Geoff Gordon

AAMAS Conference 2019 Conference Paper

Deep Generative and Discriminative Domain Adaptation

• Han Zhao
• Junjie Hu
• Zhenyao Zhu
• Adam Coates
• Geoff Gordon

The ability to adapt to and learn from different domains and environments is crucial for agents to generalize. In this paper we propose a probabilistic framework for domain adaptation that blends both generative and discriminative modeling in a principled way. Under this framework, generative and discriminative models correspond to specific choices of the prior over parameters. By maximizing both the marginal and the conditional log-likelihoods, our models can use both labeled instances from the source domain as well as unlabeled instances from both source and target domains. We show that the popular reconstruction loss of autoencoder corresponds to an upper bound of the negative marginal log-likelihoods of unlabeled instances, and give a generalization bound that explicitly incorporates it into the analysis. We instantiate our framework using neural networks, and build a concrete model, DAuto.

NeurIPS Conference 2019 Conference Paper

Inherent Tradeoffs in Learning Fair Representations

• Han Zhao
• Geoff Gordon

With the prevalence of machine learning in high-stakes applications, especially the ones regulated by anti-discrimination laws or societal norms, it is crucial to ensure that the predictive models do not propagate any existing bias or discrimination. Due to the ability of deep neural nets to learn rich representations, recent advances in algorithmic fairness have focused on learning fair representations with adversarial techniques to reduce bias in data while preserving utility simultaneously. In this paper, through the lens of information theory, we provide the first result that quantitatively characterizes the tradeoff between demographic parity and the joint utility across different population groups. Specifically, when the base rates differ between groups, we show that any method aiming to learn fair representations admits an information-theoretic lower bound on the joint error across these groups. To complement our negative results, we also prove that if the optimal decision functions across different groups are close, then learning fair representations leads to an alternative notion of fairness, known as the accuracy parity, which states that the error rates are close between groups. Finally, our theoretical findings are also confirmed empirically on real-world datasets.

RLDM Conference 2017 Conference Abstract

Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Prediction*

• Wen Sun
• Arun Venkatraman
• Geoff Gordon
• Byron Boots
• J. Bagnell

Researchers have demonstrated state-of-the-art performance in sequential decision making prob- lems (e. g. , robotics control, sequential prediction) with deep neural network models. One often has access to near-optimal oracles that achieve good performance on the task during training. We demonstrate that AggreVaTeD — a policy gradient extension of the Imitation Learning (IL) approach of (Ross & Bagnell, 2014) — can leverage such an oracle to achieve faster and better solutions with less training data than a less-informed Reinforcement Learning (RL) technique. Using both feedforward and recurrent neural pre- dictors, we present stochastic gradient procedures on a sequential prediction task, dependency-parsing from raw image data, as well as on various high dimensional robotics control problems. We also provide a comprehensive theoretical study of IL that demonstrates we can expect up to exponentially lower sample complexity for learning with AggreVaTeD than with RL algorithms, which backs our empirical findings. Our results and theory indicate that the proposed approach can achieve superior performance with respect to the oracle when the demonstrator is sub-optimal.

AAAI Conference 2012 Conference Paper

Decision Support for Agent Populations in Uncertain and Congested Environments

• Pradeep Varakantham
• Shih-Fen Cheng
• Geoff Gordon
• Asrar Ahmed

This research is motivated by large scale problems in urban transportation and labor mobility where there is congestion for resources and uncertainty in movement. In such domains, even though the individual agents do not have an identity of their own and do not explicitly interact with other agents, they effect other agents. While there has been much research in handling such implicit effects, it has primarily assumed deterministic movements of agents. We address the issue of decision support for individual agents that are identical and have involuntary movements in dynamic environments. For instance, in a taxi fleet serving a city, when a taxi is hired by a customer, its movements are uncontrolled and depend on (a) the customers requirement; and (b) the location of other taxis in the fleet. Towards addressing decision support in such problems, we make two key contributions: (a) A framework to represent the decision problem for selfish individuals in a dynamic population, where there is transitional uncertainty (involuntary movements); and (b) Two techniques (Fictitious Play for Symmetric Agent Populations, FP-SAP and Softmax based Flow Update, SMFU) that converge to equilibrium solutions. We show that our techniques (apart from providing equilibrium strategies) outperform “driver” strategies with respect to overall availability of taxis and the revenue obtained by the taxi drivers. We demonstrate this on a real world data set with 8, 000 taxis and 83 zones (representing the entire area of Singapore).

AAMAS Conference 2012 Conference Paper

Lagrangian Relaxation for Large-Scale Multi-Agent Planning

• Geoff Gordon
• Pradeep Varakantham
• William Yeoh
• Hoong Chuin Lau
• Ajay Srinivasan Aravamudhan
• Shih-Fen Cheng

Multi-agent planning is a well-studied problem with applications in various areas. Due to computational constraints, existing research typically focuses either on unstructured domains with many agents, where we are content with heuristic solutions, or domains with small numbers of agents or special structure, where we can find provably near-optimal solutions. In contrast, here we focus on provably near-optimal solutions in domains with many agents, by exploiting influence limits. To that end, we make two key contributions: (a) an algorithm, based on Lagrangian relaxation and randomized rounding, for solving multi-agent planning problems represented as large mixed-integer programs; (b) a proof of convergence of our algorithm to a near-optimal solution.

AIJ Journal 2008 Journal Article

Anytime search in dynamic graphs

• Maxim Likhachev
• Dave Ferguson
• Geoff Gordon
• Anthony Stentz
• Sebastian Thrun

Agents operating in the real world often have limited time available for planning their next actions. Producing optimal plans is infeasible in these scenarios. Instead, agents must be satisfied with the best plans they can generate within the time available. One class of planners well-suited to this task are anytime planners, which quickly find an initial, highly suboptimal plan, and then improve this plan until time runs out. A second challenge associated with planning in the real world is that models are usually imperfect and environments are often dynamic. Thus, agents need to update their models and consequently plans over time. Incremental planners, which make use of the results of previous planning efforts to generate a new plan, can substantially speed up each planning episode in such cases. In this paper, we present an A∗-based anytime search algorithm that produces significantly better solutions than current approaches, while also providing suboptimality bounds on the quality of the solution at any point in time. We also present an extension of this algorithm that is both anytime and incremental. This extension improves its current solution while deliberation time allows and is able to incrementally repair its solution when changes to the world model occur. We provide a number of theoretical and experimental results and demonstrate the effectiveness of the approaches in a robot navigation domain involving two physical systems. We believe that the simplicity, theoretical properties, and generality of the presented methods make them well suited to a range of search problems involving dynamic graphs.

AAAI Conference 2008 Conference Paper

RADAR: A Personal Assistant that Learns to Reduce Email Overload

• Michael Freed
• Geoff Gordon
• Brad Myers
• Stephen Smith

AAMAS Conference 2004 Conference Paper

Approximate Solutions for Partially Observable Stochastic Games with Common Payoffs

• Rosemary Emery-Montemerlo
• Geoff Gordon
• Jeff Schneider
• Sebastian Thrun

AAMAS Conference 2003 Conference Paper

Locating Moving Entities in Dynamic Indoor Environments with Teams of Mobile Robots

• Matthew Rosencrantz
• Geoff Gordon
• Sebastian Thrun

IJCAI Conference 2003 Conference Paper

Point-based value iteration: An anytime algorithm for POMDPs

• Joelle Pineau
• Geoff Gordon
• Sebastian Thrun

This paper introduces the Point-Based Value Iteration (PBVI) algorithm for POMDP planning. PBVI approximates an exact value iteration solution by selecting a small set of representative belief points and then tracking the value and its derivative for those points only. By using stochastic trajectories to choose belief points, and by maintaining only one value hyper-plane per point, PBVI successfully solves large problems: we present results on a robotic laser tag problem as well as three test domains from the literature.