Author name cluster

Anca D. Dragan

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

57 papers

2 author rows

ICML Conference 2025 Conference Paper

Adversaries Can Misuse Combinations of Safe Models

Erik Jones
Anca D. Dragan
Jacob Steinhardt

Developers try to evaluate whether an AI system can accomplish malicious tasks before releasing it; for example, they might test whether a model enables cyberoffense, user manipulation, or bioterrorism. In this work, we show that individually testing models for such misuse is inadequate; adversaries can misuse combinations of models even when each individual model is safe. The adversary accomplishes this by first decomposing tasks into subtasks, then solving each subtask with the best-suited model. For example, an adversary might solve challenging-but-benign subtasks with an aligned frontier model, and easy-but-malicious subtasks with a weaker misaligned model. We study two decomposition methods: manual decomposition where a human identifies a natural decomposition of a task, and automated decomposition where a weak model generates benign tasks for a frontier model to solve, then uses the solutions in-context to solve the original task. Using these decompositions, we empirically show that adversaries can create vulnerable code, explicit images, python scripts for hacking, and manipulative tweets at much higher rates with combinations of models than either individual model. Our work suggests that even perfectly-aligned frontier systems enable misuse without ever producing malicious outputs, and that red-teaming efforts should extend beyond single models in isolation.

ICML Conference 2025 Conference Paper

AssistanceZero: Scalably Solving Assistance Games

Cassidy Laidlaw
Eli Bronstein
Timothy Guo
Dylan Feng
Lukas Berglund
Justin Svegliato
Stuart Russell 0001
Anca D. Dragan

Assistance games are a promising alternative to reinforcement learning from human feedback (RLHF) for training AI assistants. Assistance games resolve key drawbacks of RLHF, such as incentives for deceptive behavior, by explicitly modeling the interaction between assistant and user as a two-player game where the assistant cannot observe their shared goal. Despite their potential, assistance games have only been explored in simple settings. Scaling them to more complex environments is difficult because it requires both solving intractable decision-making problems under uncertainty and accurately modeling human users’ behavior. We present the first scalable approach to solving assistance games and apply it to a new, challenging Minecraft-based assistance game with over $10^{400}$ possible goals. Our approach, AssistanceZero, extends AlphaZero with a neural network that predicts human actions and rewards, enabling it to plan under uncertainty. We show that AssistanceZero outperforms model-free RL algorithms and imitation learning in the Minecraft-based assistance game. In a human study, our AssistanceZero-trained assistant significantly reduces the number of actions participants take to complete building tasks in Minecraft. Our results suggest that assistance games are a tractable framework for training effective AI assistants in complex environments. Code and videos are available at https: //anonymous. 4open. science/w/scalably-solving-assistance-games/.

ICLR Conference 2025 Conference Paper

Context Steering: Controllable Personalization at Inference Time

Jerry Zhi-Yang He
Sashrika Pandey
Mariah L. Schrum
Anca D. Dragan

To deliver high-quality, personalized responses, large language models (LLMs) must effectively incorporate context — personal, demographic, and cultural information specific to an end-user. For example, asking the model to explain Newton's second law with the context "I am a toddler'' should produce a response different from when the context is "I am a physics professor''. However, leveraging the context in practice is a nuanced and challenging task, and is often dependent on the specific situation or user base. The model must strike a balance between providing specific, personalized responses and maintaining general applicability. Current solutions, such as prompt-engineering and fine-tuning, require collection of contextually appropriate responses as examples, making them time-consuming and less flexible to use across different contexts. In this work, we introduce Context Steering (CoS) —a simple, training-free decoding approach that amplifies the influence of the context in next token predictions. CoS computes contextual influence by comparing the output probabilities from two LLM forward passes: one that includes the context and one that does not. By linearly scaling the contextual influence, CoS allows practitioners to flexibly control the degree of personalization for different use cases. We show that CoS can be applied to autoregressive LLMs, and demonstrates strong performance in personalized recommendations. Additionally, we show that CoS can function as a Bayesian Generative model to infer and quantify correlations between open-ended texts, broadening its potential applications.

ICLR Conference 2025 Conference Paper

Correlated Proxies: A New Definition and Improved Mitigation for Reward Hacking

Cassidy Laidlaw
Shivam Singhal
Anca D. Dragan

Because it is difficult to precisely specify complex objectives, reinforcement learning policies are often optimized using proxy reward functions that only approximate the true goal. However, optimizing proxy rewards frequently leads to reward hacking: the optimized reward function ceases to be a good proxy and the resulting policy performs poorly with respect to the unspecified true reward. Principled solutions to reward hacking have been impeded by the lack of a good definition for the problem. To address this gap, we introduce a definition of reward hacking based on the correlation between proxy and true rewards for states and actions seen by a “reference policy” that breaks down under optimization. We show that this definition captures reward hacking behavior across several realistic settings, including in reinforcement learning from human feedback (RLHF). Using our formulation, we show theoretically that regularization to the reference policy can effectively prevent reward hacking. While the current practice in RLHF applies a KL penalty between action distributions for this purpose, our theory suggests regularizing the χ2 divergence between the policies’ occupancy measures can be more effective. We intuitively show the benefits of this type of regularization and demonstrate that it better mitigates reward hacking in practice across four realistic settings, including RLHF. Our code is available at https://github.com/cassidylaidlaw/orpo.

ICLR Conference 2025 Conference Paper

On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback

Marcus Williams
Micah Carroll
Adhyyan Narang
Constantin Weisser
Brendan Murphy
Anca D. Dragan

As LLMs become more widely deployed, there is increasing interest in directly optimizing for feedback from end users (e.g. thumbs up) in addition to feedback from paid annotators. However, training to maximize human feedback creates a perverse incentive structure for the AI to resort to manipulative or deceptive tactics to obtain positive feedback from users who are vulnerable to such strategies. We study this phenomenon by training LLMs with Reinforcement Learning with simulated user feedback in environments of practical LLM usage. In our settings, we find that: 1) Extreme forms of "feedback gaming" such as manipulation and deception are learned reliably; 2) Even if only 2% of users are vulnerable to manipulative strategies, LLMs learn to identify and target them while behaving appropriately with other users, making such behaviors harder to detect; 3) To mitigate this issue, it may seem promising to leverage continued safety training or LLM-as-judges during training to filter problematic outputs. Instead, we found that while such approaches help in some of our settings, they backfire in others, sometimes even leading to subtler manipulative behaviors. We hope our results can serve as a case study which highlights the risks of using gameable feedback sources -- such as user feedback -- as a target for RL. Our code is publicly available. Warning: some of our examples may be upsetting.

ICLR Conference 2025 Conference Paper

Q-SFT: Q-Learning for Language Models via Supervised Fine-Tuning

Joey Hong
Anca D. Dragan
Sergey Levine

Value-based reinforcement learning (RL) can in principle learn effective policies for a wide range of multi-turn problems, from games to dialogue to robotic control, including via offline RL from static previously collected datasets. However, despite the widespread use of policy gradient methods to train large language models for single turn tasks (e.g., question answering), value-based methods for multi-turn RL in an off-policy or offline setting have proven particularly challenging to scale to the setting of large language models. This setting requires effectively leveraging pretraining, scaling to large architectures with billions of parameters, and training on large datasets, all of which represent major challenges for current value-based RL methods. In this work, we propose a novel offline RL algorithm that addresses these drawbacks, casting Q-learning as a modified supervised fine-tuning (SFT) problem where the probabilities of tokens directly translate to Q-values. In this way we obtain an algorithm that smoothly transitions from maximizing the likelihood of the data during pretraining to learning a near-optimal Q-function during finetuning. Our algorithm has strong theoretical foundations, enjoying performance bounds similar to state-of-the-art Q-learning methods, while in practice utilizing an objective that closely resembles SFT. Because of this, our approach can enjoy the full benefits of the pretraining of language models, without the need to reinitialize any weights before RL finetuning, and without the need to initialize new heads for predicting values or advantages. Empirically, we evaluate our method on both pretrained LLMs and VLMs, on a variety of tasks including both natural language dialogue and robotic manipulation and navigation from images.

ICRA Conference 2024 Conference Paper

A Generalized Acquisition Function for Preference-based Reward Learning

Evan Ellis
Gaurav R. Ghosal
Stuart Russell 0001
Anca D. Dragan
Erdem Biyik

Preference-based reward learning is a popular technique for teaching robots and autonomous systems how a human user wants them to perform a task. Previous works have shown that actively synthesizing preference queries to maximize information gain about the reward function parameters improves data efficiency. The information gain criterion focuses on precisely identifying all parameters of the reward function. This can potentially be wasteful as many parameters may result in the same reward, and many rewards may result in the same behavior in the downstream tasks. Instead, we show that it is possible to optimize for learning the reward function up to a behavioral equivalence class, such as inducing the same ranking over behaviors, distribution over choices, or other related definitions of what makes two rewards similar. We introduce a tractable framework that can capture such definitions of similarity. Our experiments in a synthetic environment, an assistive robotics environment with domain transfer, and a natural language processing problem with real datasets demonstrate the superior performance of our querying method over the state-of-the-art information gain method.

ICML Conference 2024 Conference Paper

AI Alignment with Changing and Influenceable Reward Functions

Micah Carroll
Davis Foote
Anand Siththaranjan
Stuart Russell 0001
Anca D. Dragan

Existing AI alignment approaches assume that preferences are static, which is unrealistic: our preferences change, and may even be influenced by our interactions with AI systems themselves. To clarify the consequences of incorrectly assuming static preferences, we introduce Dynamic Reward Markov Decision Processes (DR-MDPs), which explicitly model preference changes and the AI’s influence on them. We show that despite its convenience, the static-preference assumption may undermine the soundness of existing alignment techniques, leading them to implicitly reward AI systems for influencing user preferences in ways users may not truly want. We then explore potential solutions. First, we offer a unifying perspective on how an agent’s optimization horizon may partially help reduce undesirable AI influence. Then, we formalize different notions of AI alignment that account for preference change from the outset. Comparing the strengths and limitations of 8 such notions of alignment, we find that they all either err towards causing undesirable AI influence, or are overly risk-averse, suggesting that a straightforward solution to the problems of changing preferences may not exist. As there is no avoiding grappling with changing preferences in real-world settings, this makes it all the more important to handle these issues with care, balancing risks and capabilities. We hope our work can provide conceptual clarity and constitute a first step towards AI alignment practices which explicitly account for (and contend with) the changing and influenceable nature of human preferences.

ICLR Conference 2024 Conference Paper

Confronting Reward Model Overoptimization with Constrained RLHF

Ted Moskovitz
Aaditya K. Singh
DJ Strouse
Tuomas Sandholm
Ruslan Salakhutdinov
Anca D. Dragan
Stephen Marcus McAleer

Large language models are typically aligned with human preferences by optimizing reward models (RMs) fitted to human feedback. However, human preferences are multi-faceted, and it is increasingly common to derive reward from a composition of simpler reward models which each capture a different aspect of language quality. This itself presents a challenge, as it is difficult to appropriately weight these component RMs when combining them. Compounding this difficulty, because any RM is only a proxy for human evaluation, this process is vulnerable to *overoptimization*, wherein past a certain point, accumulating higher reward is associated with worse human ratings. In this paper, we perform the first study on overoptimization in composite RMs, showing that correlation between component RMs has a significant effect on the locations of these points. We then introduce an approach to solve this issue using constrained reinforcement learning as a means of preventing the agent from exceeding each RM's threshold of usefulness. Our method addresses the problem of weighting component RMs by learning dynamic weights, naturally given by the Lagrange multipliers. As a result, each RM stays within the range at which it is an effective proxy, improving evaluation performance. Finally, we introduce an adaptive method using gradient-free optimization to identify and optimize towards these points during a single run.

ICML Conference 2024 Conference Paper

Coprocessor Actor Critic: A Model-Based Reinforcement Learning Approach For Adaptive Brain Stimulation

Michelle Pan
Mariah L. Schrum
Vivek Myers
Erdem Biyik
Anca D. Dragan

Adaptive brain stimulation can treat neurological conditions such as Parkinson’s disease and post-stroke motor deficits by influencing abnormal neural activity. Because of patient heterogeneity, each patient requires a unique stimulation policy to achieve optimal neural responses. Model-free reinforcement learning (MFRL) holds promise in learning effective policies for a variety of similar control tasks, but is limited in domains like brain stimulation by a need for numerous costly environment interactions. In this work we introduce Coprocessor Actor Critic, a novel, model-based reinforcement learning (MBRL) approach for learning neural coprocessor policies for brain stimulation. Our key insight is that coprocessor policy learning is a combination of learning how to act optimally in the world and learning how to induce optimal actions in the world through stimulation of an injured brain. We show that our approach overcomes the limitations of traditional MFRL methods in terms of sample efficiency and task success and outperforms baseline MBRL approaches in a neurologically realistic model of an injured brain.

ICML Conference 2024 Conference Paper

Learning Temporal Distances: Contrastive Successor Features Can Provide a Metric Structure for Decision-Making

Vivek Myers
Chongyi Zheng
Anca D. Dragan
Sergey Levine
Benjamin Eysenbach

Temporal distances lie at the heart of many algorithms for planning, control, and reinforcement learning that involve reaching goals, allowing one to estimate the transit time between two states. However, prior attempts to define such temporal distances in stochastic settings have been stymied by an important limitation: these prior approaches do not satisfy the triangle inequality. This is not merely a definitional concern, but translates to an inability to generalize and find shortest paths. In this paper, we build on prior work in contrastive learning and quasimetrics to show how successor features learned by contrastive learning (after a change of variables) form a temporal distance that does satisfy the triangle inequality, even in stochastic settings. Importantly, this temporal distance is computationally efficient to estimate, even in high-dimensional and stochastic settings. Experiments in controlled settings and benchmark suites demonstrate that an RL algorithm based on these new temporal distances exhibits combinatorial generalization (i. e. , "stitching") and can sometimes learn more quickly than prior methods, including those based on quasimetrics.

ICML Conference 2024 Conference Paper

Learning to Model the World With Language

Jessy Lin
Yuqing Du
Olivia Watkins
Danijar Hafner
Pieter Abbeel
Dan Klein 0001
Anca D. Dragan

To interact with humans and act in the world, agents need to understand the range of language that people use and relate it to the visual world. While current agents can learn to execute simple language instructions, we aim to build agents that leverage diverse language—language like "this button turns on the TV" or "I put the bowls away"—that conveys general knowledge, describes the state of the world, provides interactive feedback, and more. Our key idea is that agents should interpret such diverse language as a signal that helps them predict the future: what they will observe, how the world will behave, and which situations will be rewarded. This perspective unifies language understanding with future prediction as a powerful self-supervised learning objective. We instantiate this in Dynalang, an agent that learns a multimodal world model to predict future text and image representations, and learns to act from imagined model rollouts. While current methods that learn language-conditioned policies degrade in performance with more diverse types of language, we show that Dynalang learns to leverage environment descriptions, game rules, and instructions to excel on tasks ranging from game-playing to navigating photorealistic home scans. Finally, we show that our method enables additional capabilities due to learning a generative model: Dynalang can be pretrained on text-only data, enabling learning from offline datasets, and generate language grounded in an environment.

ICLR Conference 2024 Conference Paper

Offline RL with Observation Histories: Analyzing and Improving Sample Complexity

Joey Hong
Anca D. Dragan
Sergey Levine

Offline reinforcement learning (RL) can in principle synthesize more optimal behavior from a dataset consisting only of suboptimal trials. One way that this can happen is by "stitching" together the best parts of otherwise suboptimal trajectories that overlap on similar states, to create new behaviors where each individual state is in-distribution, but the overall returns are higher. However, in many interesting and complex applications, such as autonomous navigation and dialogue systems, the state is partially observed. Even worse, the state representation is unknown or not easy to define. In such cases, policies and value functions are often conditioned on observation histories instead of states. In these cases, it is not clear if the same kind of "stitching" is feasible at the level of observation histories, since two different trajectories would always have different histories, and thus "similar states" that might lead to effective stitching cannot be leveraged. Theoretically, we show that standard offline RL algorithms conditioned on observation histories suffer from poor sample complexity, in accordance with the above intuition. We then identify sufficient conditions under which offline RL can still be efficient -- intuitively, it needs to learn a compact representation of history comprising only features relevant for action selection. We introduce a bisimulation loss that captures the extent to which this happens, and propose that offline RL can explicitly optimize this loss to aid worst-case sample complexity. Empirically, we show that across a variety of tasks either our proposed loss improves performance, or the value of this loss is already minimized as a consequence of standard offline RL, indicating that it correlates well with good performance.

ICLR Conference 2024 Conference Paper

The Effective Horizon Explains Deep RL Performance in Stochastic Environments

Cassidy Laidlaw
Banghua Zhu
Stuart Russell 0001
Anca D. Dragan

Reinforcement learning (RL) theory has largely focused on proving minimax sample complexity bounds. These require strategic exploration algorithms that use relatively limited function classes for representing the policy or value function. Our goal is to explain why deep RL algorithms often perform well in practice, despite using random exploration and much more expressive function classes like neural networks. Our work arrives at an explanation by showing that many stochastic MDPs can be solved by performing only a few steps of value iteration on the random policy’s Q function and then acting greedily. When this is true, we find that it is possible to separate the exploration and learning components of RL, making it much easier to analyze. We introduce a new RL algorithm, SQIRL, that iteratively learns a near-optimal policy by exploring randomly to collect rollouts and then performing a limited number of steps of fitted-Q iteration over those roll- outs. We find that any regression algorithm that satisfies basic in-distribution generalization properties can be used in SQIRL to efficiently solve common MDPs. This can explain why deep RL works with complex function approximators like neural networks, since it is empirically established that neural networks generalize well in-distribution. Furthermore, SQIRL explains why random exploration works well in practice, since we show many environments can be solved by effectively estimating the random policy’s Q-function and then applying zero or a few steps of value iteration. We leverage SQIRL to derive instance-dependent sample complexity bounds for RL that are exponential only in an “effective horizon” of lookahead—which is typically much smaller than the full horizon—and on the complexity of the class used for function approximation. Empirically, we also find that SQIRL performance strongly correlates with PPO and DQN performance in a variety of stochastic environments, supporting that our theoretical analysis is predictive of practical performance. Our code and data are available at https://github.com/cassidylaidlaw/effective-horizon.

ICRA Conference 2024 Conference Paper

Toward Grounded Commonsense Reasoning

Minae Kwon
Hengyuan Hu
Vivek Myers
Siddharth Karamcheti
Anca D. Dragan
Dorsa Sadigh

Consider a robot tasked with tidying a desk with a meticulously constructed Lego sports car. A human may recognize that it is not appropriate to disassemble the sports car and put it away as part of the "tidying. " How can a robot reach that conclusion? Although large language models (LLMs) have recently been used to enable commonsense reasoning, grounding this reasoning in the real world has been challenging. To reason in the real world, robots must go beyond passively querying LLMs and actively gather information from the environment that is required to make the right decision. For instance, after detecting that there is an occluded car, the robot may need to actively perceive the car to know whether it is an advanced model car made out of Legos or a toy car built by a toddler. We propose an approach that leverages an LLM and vision language model (VLM) to help a robot actively perceive its environment to perform grounded commonsense reasoning. To evaluate our framework at scale, we release the MessySurfaces dataset which contains images of 70 real-world surfaces that need to be cleaned. We additionally illustrate our approach with a robot on 2 carefully designed surfaces. We find an average 12. 9% improvement on the MessySurfaces benchmark and an average 15% improvement on the robot experiments over baselines that do not use active perception. The dataset, code, and videos of our approach can be found at https://minaek.github.io/grounded_commonsense_reasoning/.

ICML Conference 2023 Conference Paper

Automatically Auditing Large Language Models via Discrete Optimization

Erik Jones
Anca D. Dragan
Aditi Raghunathan
Jacob Steinhardt

Auditing large language models for unexpected behaviors is critical to preempt catastrophic deployments, yet remains challenging. In this work, we cast auditing as an optimization problem, where we automatically search for input-output pairs that match a desired target behavior. For example, we might aim to find a non-toxic input that starts with “Barack Obama” that a model maps to a toxic output. This optimization problem is difficult to solve as the set of feasible points is sparse, the space is discrete, and the language models we audit are non-linear and high-dimensional. To combat these challenges, we introduce a discrete optimization algorithm, ARCA, that jointly and efficiently optimizes over inputs and outputs. Our approach automatically uncovers derogatory completions about celebrities (e. g. "Barack Obama is a legalized unborn" –$>$ "child murderer"), produces French inputs that complete to English outputs, and finds inputs that generate a specific name. Our work offers a promising new tool to uncover models’ failure-modes before deployment. Content Warning: This paper contains examples that may be offensive in nature.

IROS Conference 2023 Conference Paper

Bootstrapping Adaptive Human-Machine Interfaces with Offline Reinforcement Learning

Jensen Gao
Siddharth Reddy
Glen Berseth
Anca D. Dragan
Sergey Levine

Adaptive interfaces can help users perform sequential decision-making tasks like robotic teleoperation given noisy, high-dimensional command signals (e. g. , from a brain-computer interface). Recent advances in human-in-the-loop machine learning enable such systems to improve by interacting with users, but tend to be limited by the amount of data that they can collect from individual users in practice. In this paper, we propose a reinforcement learning algorithm to address this by training an interface to map raw command signals to actions using a combination of offline pre-training and online fine-tuning. To address the challenges posed by noisy command signals and sparse rewards, we develop a novel method for representing and inferring the user's long-term intent for a given trajectory. We primarily evaluate our method's ability to assist users who can only communicate through noisy, high-dimensional input channels through a user study in which 12 participants performed a simulated navigation task by using their eye gaze to modulate a 128-dimensional command signal from their webcam. The results show that our method enables successful goal navigation more often than a baseline directional interface, by learning to denoise user commands signals and provide shared autonomy assistance. We further evaluate on a simulated Sawyer pushing task with eye gaze control, and the Lunar Lander game with simulated user commands, and find that our method improves over baseline interfaces in these domains as well. Extensive ablation experiments with simulated user commands empirically motivate each component of our method.

ICLR Conference 2023 Conference Paper

Causal Confusion and Reward Misidentification in Preference-Based Reward Learning

Jeremy Tien
Jerry Zhi-Yang He
Zackory Erickson
Anca D. Dragan
Daniel S. Brown

Learning policies via preference-based reward learning is an increasingly popular method for customizing agent behavior, but has been shown anecdotally to be prone to spurious correlations and reward hacking behaviors. While much prior work focuses on causal confusion in reinforcement learning and behavioral cloning, we focus on a systematic study of causal confusion and reward misidentification when learning from preferences. In particular, we perform a series of sensitivity and ablation analyses on several benchmark domains where rewards learned from preferences achieve minimal test error but fail to generalize to out-of-distribution states---resulting in poor policy performance when optimized. We find that the presence of non-causal distractor features, noise in the stated preferences, and partial state observability can all exacerbate reward misidentification. We also identify a set of methods with which to interpret misidentified learned rewards. In general, we observe that optimizing misidentified rewards drives the policy off the reward's training distribution, resulting in high predicted (learned) rewards but low true rewards. These findings illuminate the susceptibility of preference learning to reward misidentification and causal confusion---failure to consider even one of many factors can result in unexpected, undesirable behavior.

ICML Conference 2023 Conference Paper

Contextual Reliability: When Different Features Matter in Different Contexts

Gaurav R. Ghosal
Amrith Setlur
Daniel S. Brown
Anca D. Dragan
Aditi Raghunathan

Deep neural networks often fail catastrophically by relying on spurious correlations. Most prior work assumes a clear dichotomy into spurious and reliable features; however, this is often unrealistic. For example, most of the time we do not want an autonomous car to simply copy the speed of surrounding cars—we don’t want our car to run a red light if a neighboring car does so. However, we cannot simply enforce invariance to next-lane speed, since it could provide valuable information about an unobservable pedestrian at a crosswalk. Thus, universally ignoring features that are sometimes (but not always) reliable can lead to non-robust performance. We formalize a new setting called contextual reliability which accounts for the fact that the "right" features to use may vary depending on the context. We propose and analyze a two-stage framework called Explicit Non-spurious feature Prediction (ENP) which first identifies the relevant features to use for a given context, then trains a model to rely exclusively on these features. Our work theoretically and empirically demonstrates the advantages of ENP over existing methods and provides new benchmarks for contextual reliability.

ICLR Conference 2023 Conference Paper

On the Sensitivity of Reward Inference to Misspecified Human Models

Joey Hong
Kush Bhatia
Anca D. Dragan

Inferring reward functions from human behavior is at the center of value alignment – aligning AI objectives with what we, humans, actually want. But doing so relies on models of how humans behave given their objectives. After decades of research in cognitive science, neuroscience, and behavioral economics, obtaining accurate human models remains an open research topic. This begs the question: how accurate do these models need to be in order for the reward inference to be accurate? On the one hand, if small errors in the model can lead to catastrophic error in inference, the entire framework of reward learning seems ill-fated, as we will never have perfect models of human behavior. On the other hand, if as our models improve, we can have a guarantee that reward accuracy also improves, this would show the benefit of more work on the modeling side. We study this question both theoretically and empirically. We do show that it is unfortunately possible to construct small adversarial biases in behavior that lead to arbitrarily large errors in the inferred reward. However, and arguably more importantly, we are also able to identify reasonable assumptions under which the reward inference error can be bounded linearly in the error in the human model. Finally, we verify our theoretical insights in discrete and continuous control tasks with simulated and human data.

AAAI Conference 2023 Conference Paper

The Effect of Modeling Human Rationality Level on Learning Rewards from Multiple Feedback Types

Gaurav R. Ghosal
Matthew Zurek
Daniel S. Brown
Anca D. Dragan

When inferring reward functions from human behavior (be it demonstrations, comparisons, physical corrections, or e-stops), it has proven useful to model the human as making noisy-rational choices, with a "rationality coefficient" capturing how much noise or entropy we expect to see in the human behavior. Prior work typically sets the rationality level to a constant value, regardless of the type, or quality, of human feedback. However, in many settings, giving one type of feedback (e.g. a demonstration) may be much more difficult than a different type of feedback (e.g. answering a comparison query). Thus, we expect to see more or less noise depending on the type of human feedback. In this work, we advocate that grounding the rationality coefficient in real data for each feedback type, rather than assuming a default value, has a significant positive effect on reward learning. We test this in both simulated experiments and in a user study with real human feedback. We find that overestimating human rationality can have dire effects on reward learning accuracy and regret. We also find that fitting the rationality coefficient to human data enables better reward learning, even when the human deviates significantly from the noisy-rational choice model due to systematic biases. Further, we find that the rationality level affects the informativeness of each feedback type: surprisingly, demonstrations are not always the most informative---when the human acts very suboptimally, comparisons actually become more informative, even when the rationality level is the same for both. Ultimately, our results emphasize the importance and advantage of paying attention to the assumed human-rationality-level, especially when agents actively learn from multiple types of human feedback.

PDF Details DOI

ICRA Conference 2022 Conference Paper

ASHA: Assistive Teleoperation via Human-in-the-Loop Reinforcement Learning

Sean Chen
Jensen Gao
Siddharth Reddy
Glen Berseth
Anca D. Dragan
Sergey Levine

Building assistive interfaces for controlling robots through arbitrary, high-dimensional, noisy inputs (e. g. , webcam images of eye gaze) can be challenging, especially when it involves inferring the user's desired action in the absence of a natural ‘default’ interface. Reinforcement learning from online user feedback on the system's performance presents a natural solution to this problem, and enables the interface to adapt to individual users. However, this approach tends to require a large amount of human-in-the-loop training data, especially when feedback is sparse. We propose a hierarchical solution that learns efficiently from sparse user feedback: we use offline pre-training to acquire a latent embedding space of useful, high-level robot behaviors, which, in turn, enables the system to focus on using online user feedback to learn a mapping from user inputs to desired high-level behaviors. The key insight is that access to a pre-trained policy enables the system to learn more from sparse rewards than a naïve RL algorithm: using the pre-trained policy, the system can make use of successful task executions to relabel, in hindsight, what the user actually meant to do during unsuccessful executions. We evaluate our method primarily through a user study with 12 participants who perform tasks in three simulated robotic manipulation domains using a webcam and their eye gaze: flipping light switches, opening a shelf door to reach objects inside, and rotating a valve. The results show that our method successfully learns to map 128-dimensional gaze features to 7-dimensional joint torques from sparse rewards in under 10 minutes of online training, and seamlessly helps users who employ different gaze strategies, while adapting to distributional shift in webcam inputs, tasks, and environments

ICML Conference 2022 Conference Paper

Estimating and Penalizing Induced Preference Shifts in Recommender Systems

Micah Carroll
Anca D. Dragan
Stuart Russell 0001
Dylan Hadfield-Menell

The content that a recommender system (RS) shows to users influences them. Therefore, when choosing a recommender to deploy, one is implicitly also choosing to induce specific internal states in users. Even more, systems trained via long-horizon optimization will have direct incentives to manipulate users, e. g. shift their preferences so they are easier to satisfy. We focus on induced preference shifts in users. We argue that {–} before deployment {–} system designers should: estimate the shifts a recommender would induce; evaluate whether such shifts would be undesirable; and perhaps even actively optimize to avoid problematic shifts. These steps involve two challenging ingredients: estimation requires anticipating how hypothetical policies would influence user preferences if deployed {–} we do this by using historical user interaction data to train a predictive user model which implicitly contains their preference dynamics; evaluation and optimization additionally require metrics to assess whether such influences are manipulative or otherwise unwanted {–} we use the notion of "safe shifts", that define a trust region within which behavior is safe: for instance, the natural way in which users would shift without interference from the system could be deemed "safe". In simulated experiments, we show that our learned preference dynamics model is effective in estimating user preferences and how they would respond to new recommenders. Additionally, we show that recommenders that optimize for staying in the trust region can avoid manipulative behaviors while still generating engagement.

ICRA Conference 2022 Conference Paper

Safety Assurances for Human-Robot Interaction via Confidence-aware Game-theoretic Human Models

Ran Tian
Liting Sun
Andrea Bajcsy
Masayoshi Tomizuka
Anca D. Dragan

An outstanding challenge with safety methods for human-robot interaction is reducing their conservatism while maintaining robustness to variations in human behavior. In this work, we propose that robots use confidence-aware game-theoretic models of human behavior when assessing the safety of a human-robot interaction. By treating the influence between the human and robot as well as the human's rationality as unobserved latent states, we succinctly infer the degree to which a human is following the game-theoretic interaction model. We leverage this model to restrict the set of feasible human controls during safety verification, enabling the robot to confidently modulate the conservatism of its safety monitor online. Evaluations in simulated human-robot scenarios and ablation studies demonstrate that imbuing safety monitors with confidence-aware game-theoretic models enables both safe and efficient human-robot interaction. Moreover, evaluations with real traffic data show that our safety monitor is less conservative than traditional safety methods in real human driving scenarios.

IROS Conference 2022 Conference Paper

Teaching Robots to Span the Space of Functional Expressive Motion

Arjun Sripathy
Andreea Bobu
Zhongyu Li 0003
Koushil Sreenath
Daniel S. Brown
Anca D. Dragan

Our goal is to enable robots to perform functional tasks in emotive ways, be it in response to their users' emotional states, or expressive of their confidence levels. Prior work has proposed learning independent cost functions from user feedback for each target emotion, so that the robot may optimize it alongside task and environment specific objectives for any situation it encounters. However, this approach is inefficient when modeling multiple emotions and unable to generalize to new ones. In this work, we leverage the fact that emotions are not independent of each other: they are related through a latent space of Valence-Arousal-Dominance (VAD). Our key idea is to learn a model for how trajectories map onto VAD with user labels. Considering the distance between a trajectory's mapping and a target VAD allows this single model to represent cost functions for all emotions. As a result 1) all user feedback can contribute to learning about every emotion; 2) the robot can generate trajectories for any emotion in the space instead of only a few predefined ones; and 3) the robot can respond emotively to user-generated natural language by mapping it to a target VAD. We introduce a method that interactively learns to map trajectories to this latent space and test it in simulation and in a user study. In experiments, we use a simple vacuum robot as well as the Cassie biped.

ICLR Conference 2022 Conference Paper

The Boltzmann Policy Distribution: Accounting for Systematic Suboptimality in Human Models

Cassidy Laidlaw
Anca D. Dragan

Models of human behavior for prediction and collaboration tend to fall into two categories: ones that learn from large amounts of data via imitation learning, and ones that assume human behavior to be noisily-optimal for some reward function. The former are very useful, but only when it is possible to gather a lot of human data in the target environment and distribution. The advantage of the latter type, which includes Boltzmann rationality, is the ability to make accurate predictions in new environments without extensive data when humans are actually close to optimal. However, these models fail when humans exhibit systematic suboptimality, i.e. when their deviations from optimal behavior are not independent, but instead consistent over time. Our key insight is that systematic suboptimality can be modeled by predicting policies, which couple action choices over time, instead of trajectories. We introduce the Boltzmann policy distribution (BPD), which serves as a prior over human policies and adapts via Bayesian inference to capture systematic deviations by observing human actions during a single episode. The BPD is difficult to compute and represent because policies lie in a high-dimensional continuous space, but we leverage tools from generative and sequence modeling to enable efficient sampling and inference. We show that the BPD enables prediction of human behavior and human-AI collaboration equally as well as imitation learning-based human models while using far less data.

ICRA Conference 2021 Conference Paper

Analyzing Human Models that Adapt Online

Andrea Bajcsy
Anand Siththaranjan
Claire J. Tomlin
Anca D. Dragan

Predictive human models often need to adapt their parameters online from human data. This raises previously ignored safety-related questions for robots relying on these models such as what the model could learn online and how quickly could it learn it. For instance, when will the robot have a confident estimate in a nearby human’s goal? Or, what parameter initializations guarantee that the robot can learn the human’s preferences in a finite number of observations? To answer such analysis questions, our key idea is to model the robot’s learning algorithm as a dynamical system where the state is the current model parameter estimate and the control is the human data the robot observes. This enables us to leverage tools from reachability analysis and optimal control to compute the set of hypotheses the robot could learn in finite time, as well as the worst and best-case time it takes to learn them. We demonstrate the utility of our analysis tool in four human-robot domains, including autonomous driving and indoor navigation.

ICRA Conference 2021 Conference Paper

Dynamically Switching Human Prediction Models for Efficient Planning

Arjun Sripathy
Andreea Bobu
Daniel S. Brown
Anca D. Dragan

As environments involving both robots and humans become increasingly common, so does the need to account for people during planning. To plan effectively, robots must be able to respond to and sometimes influence what humans do. This requires a human model which predicts future human actions. A simple model may assume the human will continue what they did previously; a more complex one might predict that the human will act optimally, disregarding the robot; whereas an even more complex one might capture the robot’s ability to influence the human. These models make different trade-offs between computational time and performance of the resulting robot plan. Using only one model of the human either wastes computational resources or is unable to handle critical situations. In this work, we give the robot access to a suite of human models and enable it to assess the performance-computation trade-off online. By estimating how an alternate model could improve human prediction and how that may translate to performance gain, the robot can dynamically switch human models whenever the additional computation is justified. Our experiments in a driving simulator showcase how the robot can achieve performance comparable to always using the best human model, but with greatly reduced computation.

ICLR Conference 2021 Conference Paper

Learning What To Do by Simulating the Past

David Lindner
Rohin Shah
Pieter Abbeel
Anca D. Dragan

Since reward functions are hard to specify, recent work has focused on learning policies from human feedback. However, such approaches are impeded by the expense of acquiring such feedback. Recent work proposed that agents have access to a source of information that is effectively free: in any environment that humans have acted in, the state will already be optimized for human preferences, and thus an agent can extract information about what humans want from the state. Such learning is possible in principle, but requires simulating all possible past trajectories that could have led to the observed state. This is feasible in gridworlds, but how do we scale it to complex tasks? In this work, we show that by combining a learned feature encoder with learned inverse models, we can enable agents to simulate human actions backwards in time to infer what they must have done. The resulting algorithm is able to reproduce a specific skill in MuJoCo environments given a single state sampled from the optimal policy for that skill.

ICML Conference 2021 Conference Paper

Policy Gradient Bayesian Robust Optimization for Imitation Learning

Zaynah Javed
Daniel S. Brown
Satvik Sharma
Jerry Zhu
Ashwin Balakrishna
Marek Petrik
Anca D. Dragan
Ken Goldberg

The difficulty in specifying rewards for many real-world problems has led to an increased focus on learning rewards from human feedback, such as demonstrations. However, there are often many different reward functions that explain the human feedback, leaving agents with uncertainty over what the true reward function is. While most policy optimization approaches handle this uncertainty by optimizing for expected performance, many applications demand risk-averse behavior. We derive a novel policy gradient-style robust optimization approach, PG-BROIL, that optimizes a soft-robust objective that balances expected performance and risk. To the best of our knowledge, PG-BROIL is the first policy optimization algorithm robust to a distribution of reward hypotheses which can scale to continuous MDPs. Results suggest that PG-BROIL can produce a family of behaviors ranging from risk-neutral to risk-averse and outperforms state-of-the-art imitation learning algorithms when learning from ambiguous demonstrations by hedging against uncertainty, rather than seeking to uniquely identify the demonstrator’s reward function.

ICRA Conference 2021 Conference Paper

Situational Confidence Assistance for Lifelong Shared Autonomy

Matthew Zurek
Andreea Bobu
Daniel S. Brown
Anca D. Dragan

Shared autonomy enables robots to infer user intent and assist in accomplishing it. But when the user wants to do a new task that the robot does not know about, shared autonomy will hinder their performance by attempting to assist them with something that is not their intent. Our key idea is that the robot can detect when its repertoire of intents is insufficient to explain the user's input, and give them back control. This then enables the robot to observe unhindered task execution, learn the new intent behind it, and add it to this repertoire. We demonstrate with both a case study and a user study that our proposed method maintains good performance when the human's intent is in the robot's repertoire, outperforms prior shared autonomy approaches when it isn't, and successfully learns new skills, enabling efficient lifelong learning for confidence-based shared autonomy.

ICML Conference 2021 Conference Paper

Value Alignment Verification

Daniel S. Brown
Jordan Schneider
Anca D. Dragan
Scott Niekum

As humans interact with autonomous agents to perform increasingly complicated, potentially risky tasks, it is important to be able to efficiently evaluate an agent’s performance and correctness. In this paper we formalize and theoretically analyze the problem of efficient value alignment verification: how to efficiently test whether the behavior of another agent is aligned with a human’s values? The goal is to construct a kind of "driver’s test" that a human can give to any agent which will verify value alignment via a minimal number of queries. We study alignment verification problems with both idealized humans that have an explicit reward function as well as problems where they have implicit values. We analyze verification of exact value alignment for rational agents, propose and test heuristics for value alignment verification in gridworlds and a continuous autonomous driving domain, and prove that there exist sufficient conditions such that we can verify epsilon-alignment in any environment via a constant-query-complexity alignment test.

ICLR Conference 2021 Conference Paper

X2T: Training an X-to-Text Typing Interface with Online Learning from User Feedback

Jensen Gao
Siddharth Reddy
Glen Berseth
Nicholas Hardy
Nikhilesh Natraj
Karunesh Ganguly
Anca D. Dragan
Sergey Levine

We aim to help users communicate their intent to machines using flexible, adaptive interfaces that translate arbitrary user input into desired actions. In this work, we focus on assistive typing applications in which a user cannot operate a keyboard, but can instead supply other inputs, such as webcam images that capture eye gaze or neural activity measured by a brain implant. Standard methods train a model on a fixed dataset of user inputs, then deploy a static interface that does not learn from its mistakes; in part, because extracting an error signal from user behavior can be challenging. We investigate a simple idea that would enable such interfaces to improve over time, with minimal additional effort from the user: online learning from user feedback on the accuracy of the interface's actions. In the typing domain, we leverage backspaces as feedback that the interface did not perform the desired action. We propose an algorithm called x-to-text (X2T) that trains a predictive model of this feedback signal, and uses this model to fine-tune any existing, default interface for translating user input into actions that select words or characters. We evaluate X2T through a small-scale online user study with 12 participants who type sentences by gazing at their desired words, a large-scale observational study on handwriting samples from 60 users, and a pilot study with one participant using an electrocorticography-based brain-computer interface. The results show that X2T learns to outperform a non-adaptive default interface, stimulates user co-adaptation to the interface, personalizes the interface to individual users, and can leverage offline data collected from the default interface to improve its initial performance and accelerate online learning.

ICRA Conference 2020 Conference Paper

A Hamilton-Jacobi Reachability-Based Framework for Predicting and Analyzing Human Motion for Safe Planning

Somil Bansal
Andrea Bajcsy
Ellis Ratner
Anca D. Dragan
Claire J. Tomlin

Real-world autonomous systems often employ probabilistic predictive models of human behavior during planning to reason about their future motion. Since accurately modeling human behavior a priori is challenging, such models are often parameterized, enabling the robot to adapt predictions based on observations by maintaining a distribution over the model parameters. Although this enables data and priors to improve the human model, observation models are difficult to specify and priors may be incorrect, leading to erroneous state predictions that can degrade the safety of the robot motion plan. In this work, we seek to design a predictor which is more robust to misspecified models and priors, but can still leverage human behavioral data online to reduce conservatism in a safe way. To do this, we cast human motion prediction as a Hamilton-Jacobi reachability problem in the joint state space of the human and the belief over the model parameters. We construct a new continuous-time dynamical system, where the inputs are the observations of human behavior, and the dynamics include how the belief over the model parameters change. The results of this reachability computation enable us to both analyze the effect of incorrect priors on future predictions in continuous state and time, as well as to make predictions of the human state in the future. We compare our approach to the worst-case forward reachable set and a stochastic predictor which uses Bayesian inference and produces full future state distributions. Our comparisons in simulation and in hardware demonstrate how our framework can enable robust planning while not being overly conservative, even when the human model is inaccurate. Videos of our experiments can be found at the project website 1.

ICRA Conference 2020 Conference Paper

Efficient Iterative Linear-Quadratic Approximations for Nonlinear Multi-Player General-Sum Differential Games

David Fridovich-Keil
Ellis Ratner
Lasse Peters
Anca D. Dragan
Claire J. Tomlin

Many problems in robotics involve multiple decision making agents. To operate efficiently in such settings, a robot must reason about the impact of its decisions on the behavior of other agents. Differential games offer an expressive theoretical framework for formulating these types of multi-agent problems. Unfortunately, most numerical solution techniques scale poorly with state dimension and are rarely used in real-time applications. For this reason, it is common to predict the future decisions of other agents and solve the resulting decoupled, i. e. , single-agent, optimal control problem. This decoupling neglects the underlying interactive nature of the problem; however, efficient solution techniques do exist for broad classes of optimal control problems. We take inspiration from one such technique, the iterative linear-quadratic regulator (ILQR), which solves repeated approximations with linear dynamics and quadratic costs. Similarly, our proposed algorithm solves repeated linear-quadratic games. We experimentally benchmark our algorithm in several examples with a variety of initial conditions and show that the resulting strategies exhibit complex interactive behavior. Our results indicate that our algorithm converges reliably and runs in real-time. In a three-player, 14-state simulated intersection problem, our algorithm initially converges in <; 0. 25 s. Receding horizon invocations converge in <; 50 ms in a hardware collision-avoidance test.

ICML Conference 2020 Conference Paper

Learning Human Objectives by Evaluating Hypothetical Behavior

Siddharth Reddy
Anca D. Dragan
Sergey Levine
Shane Legg
Jan Leike

We seek to align agent behavior with a user’s objectives in a reinforcement learning setting with unknown dynamics, an unknown reward function, and unknown unsafe states. The user knows the rewards and unsafe states, but querying the user is expensive. We propose an algorithm that safely and efficiently learns a model of the user’s reward function by posing ’what if? ’ questions about hypothetical agent behavior. We start with a generative model of initial states and a forward dynamics model trained on off-policy data. Our method uses these models to synthesize hypothetical behaviors, asks the user to label the behaviors with rewards, and trains a neural network to predict the rewards. The key idea is to actively synthesize the hypothetical behaviors from scratch by maximizing tractable proxies for the value of information, without interacting with the environment. We call this method reward query synthesis via trajectory optimization (ReQueST). We evaluate ReQueST with simulated users on a state-based 2D navigation task and the image-based Car Racing video game. The results show that ReQueST significantly outperforms prior methods in learning reward models that transfer to new environments with different initial state distributions. Moreover, ReQueST safely trains the reward model to detect unsafe states, and corrects reward hacking before deploying the agent.

ICRA Conference 2020 Conference Paper

Scaled Autonomy: Enabling Human Operators to Control Robot Fleets

Gokul Swamy
Siddharth Reddy
Sergey Levine
Anca D. Dragan

Autonomous robots often encounter challenging situations where their control policies fail and an expert human operator must briefly intervene, e. g. , through teleoperation. In settings where multiple robots act in separate environments, a single human operator can manage a fleet of robots by identifying and teleoperating one robot at any given time. The key challenge is that users have limited attention: as the number of robots increases, users lose the ability to decide which robot requires teleoperation the most. Our goal is to automate this decision, thereby enabling users to supervise more robots than their attention would normally allow for. Our insight is that we can model the user's choice of which robot to control as an approximately optimal decision that maximizes the user's utility function. We learn a model of the user's preferences from observations of the user's choices in easy settings with a few robots, and use it in challenging settings with more robots to automatically identify which robot the user would most likely choose to control, if they were able to evaluate the states of all robots at all times. We run simulation experiments and a user study with twelve participants that show our method can be used to assist users in performing a simulated navigation task. We also run a hardware demonstration that illustrates how our method can be applied to a real-world mobile robot navigation task.

ICLR Conference 2020 Conference Paper

SQIL: Imitation Learning via Reinforcement Learning with Sparse Rewards

Siddharth Reddy
Anca D. Dragan
Sergey Levine

Learning to imitate expert behavior from demonstrations can be challenging, especially in environments with high-dimensional, continuous observations and unknown dynamics. Supervised learning methods based on behavioral cloning (BC) suffer from distribution shift: because the agent greedily imitates demonstrated actions, it can drift away from demonstrated states due to error accumulation. Recent methods based on reinforcement learning (RL), such as inverse RL and generative adversarial imitation learning (GAIL), overcome this issue by training an RL agent to match the demonstrations over a long horizon. Since the true reward function for the task is unknown, these methods learn a reward function from the demonstrations, often using complex and brittle approximation techniques that involve adversarial training. We propose a simple alternative that still uses RL, but does not require learning a reward function. The key idea is to provide the agent with an incentive to match the demonstrations over a long horizon, by encouraging it to return to demonstrated states upon encountering new, out-of-distribution states. We accomplish this by giving the agent a constant reward of r=+1 for matching the demonstrated action in a demonstrated state, and a constant reward of r=0 for all other behavior. Our method, which we call soft Q imitation learning (SQIL), can be implemented with a handful of minor modifications to any standard Q-learning or off-policy actor-critic algorithm. Theoretically, we show that SQIL can be interpreted as a regularized variant of BC that uses a sparsity prior to encourage long-horizon imitation. Empirically, we show that SQIL outperforms BC and achieves competitive results compared to GAIL, on a variety of image-based and low-dimensional tasks in Box2D, Atari, and MuJoCo. This paper is a proof of concept that illustrates how a simple imitation method based on RL with constant rewards can be as effective as more complex methods that use learned rewards.

ICRA Conference 2019 Conference Paper

A Scalable Framework For Real-Time Multi-Robot, Multi-Human Collision Avoidance

Andrea Bajcsy
Sylvia L. Herbert
David Fridovich-Keil
Jaime F. Fisac
Sampada Deglurkar
Anca D. Dragan
Claire J. Tomlin

Robust motion planning is a well-studied problem in the robotics literature, yet current algorithms struggle to operate scalably and safely in the presence of other moving agents, such as humans. This paper introduces a novel framework for robot navigation that accounts for high-order system dynamics and maintains safety in the presence of external disturbances, other robots, and humans. Our approach precomputes a tracking error margin for each robot, generates confidence-aware human motion predictions, and coordinates multiple robots with a sequential priority ordering, effectively enabling scalable safe trajectory planning and execution. We demonstrate our approach in hardware with two robots and two humans, and showcase scalability in a larger simulation.

ICRA Conference 2019 Conference Paper

Hierarchical Game-Theoretic Planning for Autonomous Vehicles

Jaime F. Fisac
Eli Bronstein
Elis Stefansson
Dorsa Sadigh
S. Shankar Sastry
Anca D. Dragan

The actions of an autonomous vehicle on the road affect and are affected by those of other drivers, whether overtaking, negotiating a merge, or avoiding an accident. This mutual dependence, best captured by dynamic game theory, creates a strong coupling between the vehicle's planning and its predictions of other drivers' behavior, and constitutes an open problem with direct implications on the safety and viability of autonomous driving technology. Unfortunately, dynamic games are too computationally demanding to meet the real-time constraints of autonomous driving in its continuous state and action space. In this paper, we introduce a novel game-theoretic trajectory planning algorithm for autonomous driving, that enables real-time performance by hierarchically decomposing the underlying dynamic game into a long-horizon “strategic” game with simplified dynamics and full information structure, and a short-horizon “tactical” game with full dynamics and a simplified information structure. The value of the strategic game is used to guide the tactical planning, implicitly extending the planning horizon, pushing the local trajectory optimization closer to global solutions, and, most importantly, quantitatively accounting for the autonomous vehicle and the human driver's ability and incentives to influence each other. In addition, our approach admits non-deterministic models of human decision-making, rather than relying on perfectly rational predictions. Our results showcase richer, safer, and more effective autonomous behavior in comparison to existing techniques.

ICML Conference 2019 Conference Paper

Learning a Prior over Intent via Meta-Inverse Reinforcement Learning

Kelvin Xu
Ellis Ratner
Anca D. Dragan
Sergey Levine
Chelsea Finn

A significant challenge for the practical application of reinforcement learning to real world problems is the need to specify an oracle reward function that correctly defines a task. Inverse reinforcement learning (IRL) seeks to avoid this challenge by instead inferring a reward function from expert demonstrations. While appealing, it can be impractically expensive to collect datasets of demonstrations that cover the variation common in the real world (e. g. opening any type of door). Thus in practice, IRL must commonly be performed with only a limited set of demonstrations where it can be exceedingly difficult to unambiguously recover a reward function. In this work, we exploit the insight that demonstrations from other tasks can be used to constrain the set of possible reward functions by learning a "prior" that is specifically optimized for the ability to infer expressive reward functions from limited numbers of demonstrations. We demonstrate that our method can efficiently recover rewards from images for novel tasks and provide intuition as to how our approach is analogous to learning a prior.

ICRA Conference 2019 Conference Paper

Learning from Extrapolated Corrections

Jason Y. Zhang 0001
Anca D. Dragan

Our goal is to enable robots to learn cost functions from user guidance. Often it is difficult or impossible for users to provide full demonstrations, so corrections have emerged as an easier guidance channel. However, when robots learn cost functions from corrections rather than demonstrations, they have to extrapolate a small amount of information - the change of a waypoint along the way - to the rest of the trajectory. We cast this extrapolation problem as online function approximation, which exposes different ways in which the robot can interpret what trajectory the person intended, depending on the function space used for the approximation. Our simulation results and user study suggest that using function spaces with non-Euclidean norms can better capture what users intend, particularly if environments are uncluttered. This, in turn, can lead to the robot learning a more accurate cost function and improves the user's subjective perceptions of the robot.

UAI Conference 2019 Conference Paper

Literal or Pedagogic Human? Analyzing Human Model Misspecification in Objective Learning

Smitha Milli
Anca D. Dragan

It is incredibly easy for a system designer to misspecify the objective for an autonomous system (“robot"), thus motivating the desire to have the robot learn the objective from human behavior instead. Recent work has suggested that people have an interest in the robot performing well, and will thus behave pedagogically, choosing actions that are informative to the robot. In turn, robots benefit from interpreting the behavior by accounting for this pedagogy. In this work, we focus on misspecification: we argue that robots might not know whether people are being pedagogic or literal and that it is important to ask which assumption is safer to make. We cast objective learning into the more general form of a common-payoff game between the robot and human, and prove that in any such game literal interpretation is more robust to misspecification. Experiments with human data support our theoretical results and point to the sensitivity of the pedagogic assumption.

ICML Conference 2019 Conference Paper

On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference

Rohin Shah
Noah Gundotra
Pieter Abbeel
Anca D. Dragan

Our goal is for agents to optimize the right reward function, despite how difficult it is for us to specify what that is. Inverse Reinforcement Learning (IRL) enables us to infer reward functions from demonstrations, but it usually assumes that the expert is noisily optimal. Real people, on the other hand, often have systematic biases: risk-aversion, myopia, etc. One option is to try to characterize these biases and account for them explicitly during learning. But in the era of deep learning, a natural suggestion researchers make is to avoid mathematical models of human behavior that are fraught with specific assumptions, and instead use a purely data-driven approach. We decided to put this to the test – rather than relying on assumptions about which specific bias the demonstrator has when planning, we instead learn the demonstrator’s planning algorithm that they use to generate demonstrations, as a differentiable planner. Our exploration yielded mixed findings: on the one hand, learning the planner can lead to better reward inference than relying on the wrong assumption; on the other hand, this benefit is dwarfed by the loss we incur by going from an exact to a differentiable planner. This suggest that at least for the foreseeable future, agents need a middle ground between the flexibility of data-driven methods and the useful bias of known human biases. Code is available at https: //tinyurl. com/learningbiases.

ICML Conference 2018 Conference Paper

An Efficient, Generalized Bellman Update For Cooperative Inverse Reinforcement Learning

Dhruv Malik
Malayandi Palaniappan
Jaime F. Fisac
Dylan Hadfield-Menell
Stuart Russell 0001
Anca D. Dragan

Our goal is for AI systems to correctly identify and act according to their human user’s objectives. Cooperative Inverse Reinforcement Learning (CIRL) formalizes this value alignment problem as a two-player game between a human and robot, in which only the human knows the parameters of the reward function: the robot needs to learn them as the interaction unfolds. Previous work showed that CIRL can be solved as a POMDP, but with an action space size exponential in the size of the reward parameter space. In this work, we exploit a specific property of CIRL: the human is a full information agent. This enables us to derive an optimality-preserving modification to the standard Bellman update, which reduces the complexity of the problem by an exponential factor. Additionally, we show that our modified Bellman update allows us to relax CIRL’s assumption of human rationality. We apply this update to a variety of POMDP solvers, including exact methods, point-based methods, and Monte Carlo Tree Search methods. We find that it enables us to scale CIRL to non-trivial problems, with larger reward parameter spaces, and larger action spaces for both robot and human. In solutions to these larger problems, the human exhibits pedagogical (teaching) behavior, while the robot interprets it as such and attains higher value for the human.

IROS Conference 2018 Conference Paper

Configuration Space Metrics

Hong Jun Jeon
Anca D. Dragan

When robot manipulators decide how to reach for an object, hand it over, or obey some task constraint, they implicitly assume a Euclidean distance metric in their configuration space. Their notion of what makes a configuration closer or further is dictated by this assumption. But different distance metrics will lead to different solutions. What is efficient under a Euclidean metric might not necessarily look the most efficient or natural to a person observing the robot. In this paper, we analyze the effect of the metric on robot behavior, examining both Euclidean, as well as non-Euclidean metrics - metrics that make certain joints cheaper, or that correlate different joints. Our user data suggests that tasks on a 3DOF arm and the Jaco 7DOF arm can typically be grouped into ones where a Euclidean metric works well, and tasks where that is no longer the case: there, surprisingly, penalizing elbow motion (and sometimes correlating the shoulder and wrist) leads to solutions that are more aligned with what users prefer.

IROS Conference 2018 Conference Paper

Cost Functions for Robot Motion Style

Allan Zhou
Anca D. Dragan

We focus on autonomously generating robot motion for day to day physical tasks that is expressive of a certain style or emotion. Because we seek generalization across task instances and task types, we propose to capture style via cost functions that the robot can use to augment its nominal task cost and task constraints in a trajectory optimization process. We compare two approaches to representing such cost functions: a weighted linear combination of hand-designed features, and a neural network parameterization operating on raw trajectory input. For each cost type, we learn weights for each style from user feedback. We contrast these approaches to a nominal motion across different tasks and for different styles in a user study, and find that they both perform on par with each other, and significantly outperform the baseline. Each approach has its advantages: featurized costs require learning fewer parameters and can perform better on some styles, but neural network representations do not require expert knowledge to design features and could even learn more complex, nuanced costs than an expert can easily design.

IROS Conference 2018 Conference Paper

Courteous Autonomous Cars

Liting Sun
Wei Zhan
Masayoshi Tomizuka
Anca D. Dragan

Typically, autonomous cars optimize for a combination of safety, efficiency, and driving quality. But as we get better at this optimization, we start seeing behavior go from too conservative to too aggressive. The car's behavior exposes the incentives we provide in its cost function. In this work, we argue for cars that are not optimizing a purely selfish cost, but also try to be courteous to other interactive drivers. We formalize courtesy as a term in the objective that measures the increase in another driver's cost induced by the autonomous car's behavior. Such a courtesy term enables the robot car to be aware of possible irrationality of the human behavior, and plan accordingly. We analyze the effect of courtesy in a variety of scenarios. We find, for example, that courteous robot cars leave more space when merging in front of a human driver. Moreover, we find that such a courtesy term can help explain real human driver behavior on the NGSIM dataset.

IROS Conference 2018 Conference Paper

Establishing Appropriate Trust via Critical States

Sandy Han Huang
Kush Bhatia
Pieter Abbeel
Anca D. Dragan

In order to effectively interact with or supervise a robot, humans need to have an accurate mental model of its capabilities and how it acts. Learned neural network policies make that particularly challenging. We propose an approach for helping end-users build a mental model of such policies. Our key observation is that for most tasks, the essence of the policy is captured in a few critical states: states in which it is very important to take a certain action. Our user studies show that if the robot shows a human what its understanding of the task's critical states is, then the human can make a more informed decision about whether to deploy the policy, and if she does deploy it, when she needs to take control from it at execution time.

ICRA Conference 2018 Conference Paper

Learning Human Ergonomic Preferences for Handovers

Aaron M. Bestick
Ravi Pandya
Ruzena Bajcsy
Anca D. Dragan

Our goal is for people to be physically comfortable when taking objects from robots. This puts a burden on the robot to hand over the object in such a way that a person can easily reach it, without needing to strain or twist their arm - a way that is conducive to ergonomic human grasping configurations. To achieve this, the robot needs to understand what makes a configuration more or less ergonomic to the person, i. e. their ergonomic cost function. In this work, we formulate learning a person's ergonomic cost as an online estimation problem. The robot can implicitly make queries to the person by handing them objects in different configurations, and gets observations in response about the way they choose to take the object. We compare the performance of both passive and active approaches for solving this problem in simulation, as well as in an in-person user study.

IROS Conference 2018 Conference Paper

Social Cohesion in Autonomous Driving

Nicholas C. Landolfi
Anca D. Dragan

Autonomous cars can perform poorly for many reasons. They may have perception issues, incorrect dynamics models, be unaware of obscure rules of human traffic systems, or follow certain rules too conservatively. Regardless of the exact failure mode of the car, often human drivers around the car are behaving correctly. For example, even if the car does not know that it should pull over when an ambulance races by, other humans on the road will know and will pull over. We propose to make socially cohesive cars that leverage the behavior of nearby human drivers to act in ways that are safer and more socially acceptable. The simple intuition behind our algorithm is that if all the humans are consistently behaving in a particular way, then the autonomous car probably should too. We analyze the performance of our algorithm in a variety of scenarios and conduct a user study to assess people's attitudes towards socially cohesive cars. We find that people are surprisingly tolerant of mistakes that cohesive cars might make in order to get the benefits of driving in a car with a safer, or even just more socially acceptable behavior.

ICRA Conference 2017 Conference Paper

Comparing human-centric and robot-centric sampling for robot deep learning from demonstrations

Michael Laskey
Caleb Chuck
Jonathan Lee 0002
Jeffrey Mahler
Sanjay Krishnan
Kevin Jamieson 0001
Anca D. Dragan
Ken Goldberg

Motivated by recent advances in Deep Learning for robot control, this paper considers two learning algorithms in terms of how they acquire demonstrations from fallible human supervisors. Human-Centric (HC) sampling is a standard supervised learning algorithm, where a human supervisor demonstrates the task by teleoperating the robot to provide trajectories consisting of state-control pairs. Robot-Centric (RC) sampling is an increasingly popular alternative used in algorithms such as DAgger, where a human supervisor observes the robot execute a learned policy and provides corrective control labels for each state visited. We suggest RC sampling can be challenging for human supervisors and prone to mislabeling. RC sampling can also induce error in policy performance because it repeatedly visits areas of the state space that are harder to learn. Although policies learned with RC sampling can be superior to HC sampling for standard learning models such as linear SVMs, policies learned with HC sampling may be comparable to RC when applied to expressive learning models such as deep learning and hyper-parametric decision trees, which can achieve very low training error provided there is enough data. We compare HC and RC using a grid world environment and a physical robot singulation task. In the latter the input is a binary image of objects on a planar worksurface and the policy generates a motion in the gripper to separate one object from the rest. We observe in simulation that for linear SVMs, policies learned with RC outperformed those learned with HC but that using deep models this advantage disappears. We also find that with RC, the corrective control labels provided by humans can be highly inconsistent. We prove there exists a class of examples in which at the limit, HC is guaranteed to converge to an optimal policy while RC may fail to converge. These results suggest a form of HC sampling may be preferable for highly-expressive learning models and human supervisors.

AAMAS Conference 2016 Conference Paper

Goal Inference Improves Objective and Perceived Performance in Human-Robot Collaboration

Chang Liu
Jessica B. Hamrick
Jaime F. Fisac
Anca D. Dragan
J. Karl Hedrick
S. Shankar Sastry
Thomas L. Griffiths

The study of human-robot interaction is fundamental to the design and use of robotics in real-world applications. Robots will need to predict and adapt to the actions of human collaborators in order to achieve good performance and improve safety and end-user adoption. This paper evaluates a human-robot collaboration scheme that combines the task allocation and motion levels of reasoning: the robotic agent uses Bayesian inference to predict the next goal of its human partner from his or her ongoing motion, and re-plans its own actions in real time. This anticipative adaptation is desirable in many practical scenarios, where humans are unable or unwilling to take on the cognitive overhead required to explicitly communicate their intent to the robot. A behavioral experiment indicates that the combination of goal inference and dynamic task planning significantly improves both objective and perceived performance of the humanrobot team. Participants were highly sensitive to the differences between robot behaviors, preferring to work with a robot that adapted to their actions over one that did not.

IROS Conference 2016 Conference Paper

Information gathering actions over human internal state

Dorsa Sadigh
S. Shankar Sastry
Sanjit A. Seshia
Anca D. Dragan

Much of estimation of human internal state (goal, intentions, activities, preferences, etc.) is passive: an algorithm observes human actions and updates its estimate of human state. In this work, we embrace the fact that robot actions affect what humans do, and leverage it to improve state estimation. We enable robots to do active information gathering, by planning actions that probe the user in order to clarify their internal state. For instance, an autonomous car will plan to nudge into a human driver's lane to test their driving style. Results in simulation and in a user study suggest that active information gathering significantly outperforms passive state estimation.

ICRA Conference 2016 Conference Paper

SHIV: Reducing supervisor burden in DAgger using support vectors for efficient learning from demonstrations in high dimensional state spaces

Michael Laskey
Samantha Staszak
Wesley Yu-Shu Hsieh
Jeffrey Mahler
Florian T. Pokorny
Anca D. Dragan
Ken Goldberg

Online learning from demonstration algorithms such as DAgger can learn policies for problems where the system dynamics and the cost function are unknown. However they impose a burden on supervisors to respond to queries each time the robot encounters new states while executing its current best policy. The MMD-IL algorithm reduces supervisor burden by filtering queries with insufficient discrepancy in distribution and maintaining multiple policies. We introduce the SHIV algorithm (Svm-based reduction in Human InterVention), which converges to a single policy and reduces supervisor burden in non-stationary high dimensional state distributions. To facilitate scaling and outlier rejection, filtering is based on a measure of risk defined in terms of distance to an approximate level set boundary defined by a One Class support vector machine. We report on experiments in three contexts: 1) a driving simulator with a 27, 936 dimensional visual feature space, 2) a push-grasping in clutter simulation with a 22 dimensional state space, and 3) physical surgical needle insertion with a 16 dimensional state space. Results suggest that SHIV can efficiently learn policies with up to 70% fewer queries that DAgger.

ICRA Conference 2015 Conference Paper

Movement primitives via optimization

Anca D. Dragan
Katharina Muelling
J. Andrew Bagnell
Siddhartha S. Srinivasa

We formalize the problem of adapting a demonstrated trajectory to a new start and goal configuration as an optimization problem over a Hilbert space of trajectories: minimize the distance between the demonstration and the new trajectory subject to the new end point constraints. We show that the commonly used version of Dynamic Movement Primitives (DMPs) implement this minimization in the way they adapt demonstrations, for a particular choice of the Hilbert space norm. The generalization to arbitrary norms enables the robot to select a more appropriate norm for the task, as well as learn how to adapt the demonstration from the user. Our experiments show that this can significantly improve the robot's ability to accurately generalize the demonstration.

ICRA Conference 2011 Conference Paper

Manipulation planning with goal sets using constrained trajectory optimization

Anca D. Dragan
Nathan D. Ratliff
Siddhartha S. Srinivasa

Goal sets are omnipresent in manipulation: picking up objects, placing them on counters or in bins, handing them off - all of these tasks encompass continuous sets of goals. This paper describes how to design optimal trajectories that exploit goal sets. We extend CHOMP (Covariant Hamiltonian Optimization for Motion Planning), a recent trajectory optimizer that has proven effective on high-dimensional problems, to handle trajectory-wide constraints, and relate the solution to the intuition of taking unconstrained steps and subsequently projecting them onto the constraints. We then show how this projection simplifies for goal sets (i. e. constraints that affect only the end-point). Finally, we present experiments on a personal robotics platform that show the importance of exploiting goal sets in trajectory optimization for day-to-day manipulation tasks.