Author name cluster

Omer Gottesman

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.

13 papers

2 author rows

ICLR Conference 2025 Conference Paper

Geometry of Neural Reinforcement Learning in Continuous State and Action Spaces

Saket Tiwari
Omer Gottesman
George Konidaris 0001

Advances in reinforcement learning (RL) have led to its successful application in complex tasks with continuous state and action spaces. Despite these advances in practice, most theoretical work pertains to finite state and action spaces. We propose building a theoretical understanding of continuous state and action spaces by employing a geometric lens to understand the locally attained set of states. The set of all parametrised policies learnt through a semi-gradient based approach induce a set of attainable states in RL. We show that training dynamics of a two layer neural policy induce a low dimensional manifold of attainable states embedded in the high-dimensional nominal state space trained using an actor-critic algorithm. We prove that, under certain conditions, the dimensionality of this manifold is of the order of the dimensionality of the action space. This is the first result of its kind, linking the geometry of the state space to the dimensionality of the action space. We empirically corroborate this upper bound for four MuJoCo environments and also demonstrate the results in a toy environment with varying dimensionality. We also show the applicability of this theoretical result by introducing a local manifold learning layer to the policy and value function networks to improve the performance in control environments with very high degrees of freedom by changing one layer of the neural network to learn sparse representations.

Details

NeurIPS Conference 2024 Conference Paper

Mitigating Partial Observability in Sequential Decision Processes via the Lambda Discrepancy

Cameron Allen
Aaron Kirtland
Ruo Yu Tao
Sam Lobel
Daniel Scott
Nicholas Petrocelli
Omer Gottesman
Ronald Parr

Reinforcement learning algorithms typically rely on the assumption that the environment dynamics and value function can be expressed in terms of a Markovian state representation. However, when state information is only partially observable, how can an agent learn such a state representation, and how can it detect when it has found one? We introduce a metric that can accomplish both objectives, without requiring access to---or knowledge of---an underlying, unobservable state space. Our metric, the λ-discrepancy, is the difference between two distinct temporal difference (TD) value estimates, each computed using TD(λ) with a different value of λ. Since TD(λ=0) makes an implicit Markov assumption and TD(λ=1) does not, a discrepancy between these estimates is a potential indicator of a non-Markovian state representation. Indeed, we prove that the λ-discrepancy is exactly zero for all Markov decision processes and almost always non-zero for a broad class of partially observable environments. We also demonstrate empirically that, once detected, minimizing the λ-discrepancy can help with learning a memory function to mitigate the corresponding partial observability. We then train a reinforcement learning agent that simultaneously constructs two recurrent value networks with different λ parameters and minimizes the difference between them as an auxiliary loss. The approach scales to challenging partially observable domains, where the resulting agent frequently performs significantly better (and never performs worse) than a baseline recurrent agent with only a single value network.

PDF Details DOI

NeurIPS Conference 2023 Conference Paper

Effectively Learning Initiation Sets in Hierarchical Reinforcement Learning

Akhil Bagaria
Ben Abbatematteo
Omer Gottesman
Matt Corsaro
Sreehari Rammohan
George Konidaris

An agent learning an option in hierarchical reinforcement learning must solve three problems: identify the option's subgoal (termination condition), learn a policy, and learn where that policy will succeed (initiation set). The termination condition is typically identified first, but the option policy and initiation set must be learned simultaneously, which is challenging because the initiation set depends on the option policy, which changes as the agent learns. Consequently, data obtained from option execution becomes invalid over time, leading to an inaccurate initiation set that subsequently harms downstream task performance. We highlight three issues---data non-stationarity, temporal credit assignment, and pessimism---specific to learning initiation sets, and propose to address them using tools from off-policy value estimation and classification. We show that our method learns higher-quality initiation sets faster than existing methods (in MiniGrid and Montezuma's Revenge), can automatically discover promising grasps for robot manipulation (in Robosuite), and improves the performance of a state-of-the-art option discovery method in a challenging maze navigation task in MuJoCo.

PDF Details

ICLR Conference 2023 Conference Paper

Performance Bounds for Model and Policy Transfer in Hidden-parameter MDPs

Haotian Fu
Jiayu Yao
Omer Gottesman
Finale Doshi
George Konidaris 0001

In the Hidden-Parameter MDP (HiP-MDP) framework, a family of reinforcement learning tasks is generated by varying hidden parameters specifying the dynamics and reward function for each individual task. HiP-MDP is a natural model for families of tasks in which meta- and lifelong-reinforcement learning approaches can succeed. Given a learned context encoder that infers the hidden parameters from previous experience, most existing algorithms fall into two categories: $\textit{model transfer}$ and $\textit{policy transfer}$, depending on which function the hidden parameters are used to parameterize. We characterize the robustness of model and policy transfer algorithms with respect to hidden parameter estimation error. We first show that the value function of HiP-MDPs is Lipschitz continuous under certain conditions. We then derive regret bounds for both settings through the lens of Lipschitz continuity. Finally, we empirically corroborate our theoretical analysis by experimentally varying the hyper-parameters governing the Lipschitz constants of two continuous control problems; the resulting performance is consistent with our predictions.

Details

NeurIPS Conference 2023 Conference Paper

TD Convergence: An Optimization Perspective

Kavosh Asadi
Shoham Sabach
Yao Liu
Omer Gottesman
Rasool Fakoor

We study the convergence behavior of the celebrated temporal-difference (TD) learning algorithm. By looking at the algorithm through the lens of optimization, we first argue that TD can be viewed as an iterative optimization algorithm where the function to be minimized changes per iteration. By carefully investigating the divergence displayed by TD on a classical counter example, we identify two forces that determine the convergent or divergent behavior of the algorithm. We next formalize our discovery in the linear TD setting with quadratic loss and prove that convergence of TD hinges on the interplay between these two forces. We extend this optimization perspective to prove convergence of TD in a much broader setting than just linear approximation and squared loss. Our results provide a theoretical explanation for the successful application of TD in reinforcement learning.

PDF Details

NeurIPS Conference 2022 Conference Paper

Faster Deep Reinforcement Learning with Slower Online Network

Kavosh Asadi
Rasool Fakoor
Omer Gottesman
Taesup Kim
Michael Littman
Alexander J. Smola

Deep reinforcement learning algorithms often use two networks for value function optimization: an online network, and a target network that tracks the online network with some delay. Using two separate networks enables the agent to hedge against issues that arise when performing bootstrapping. In this paper we endow two popular deep reinforcement learning algorithms, namely DQN and Rainbow, with updates that incentivize the online network to remain in the proximity of the target network. This improves the robustness of deep reinforcement learning in presence of noisy updates. The resultant agents, called DQN Pro and Rainbow Pro, exhibit significant performance improvements over their original counterparts on the Atari benchmark demonstrating the effectiveness of this simple idea in deep reinforcement learning. The code for our paper is available here: Github. com/amazon-research/fast-rl-with-slow-updates.

PDF Details

AAAI Conference 2022 Conference Paper

Optimistic Initialization for Exploration in Continuous Control

Sam Lobel
Omer Gottesman
Cameron Allen
Akhil Bagaria
George Konidaris

Optimistic initialization underpins many theoretically sound exploration schemes in tabular domains; however, in the deep function approximation setting, optimism can quickly disappear if initialized naı̈vely. We propose a framework for more effectively incorporating optimistic initialization into reinforcement learning for continuous control. Our approach uses metric information about the state-action space to estimate which transitions are still unexplored, and explicitly maintains the initial Q-value optimism for the corresponding state-action pairs. We also develop methods for efficiently approximating these training objectives, and for incorporating domain knowledge into the optimistic envelope to improve sample efficiency. We empirically evaluate these approaches on a variety of hard exploration problems in continuous control, where our method outperforms existing exploration techniques.

PDF Details

NeurIPS Conference 2021 Conference Paper

Learning Markov State Abstractions for Deep Reinforcement Learning

Cameron Allen
Neev Parikh
Omer Gottesman
George Konidaris

A fundamental assumption of reinforcement learning in Markov decision processes (MDPs) is that the relevant decision process is, in fact, Markov. However, when MDPs have rich observations, agents typically learn by way of an abstract state representation, and such representations are not guaranteed to preserve the Markov property. We introduce a novel set of conditions and prove that they are sufficient for learning a Markov abstract state representation. We then describe a practical training procedure that combines inverse model estimation and temporal contrastive learning to learn an abstraction that approximately satisfies these conditions. Our novel training objective is compatible with both online and offline training: it does not require a reward signal, but agents can capitalize on reward information when available. We empirically evaluate our approach on a visual gridworld domain and a set of continuous control benchmarks. Our approach learns representations that capture the underlying structure of the domain and lead to improved sample efficiency over state-of-the-art deep reinforcement learning with visual features---often matching or exceeding the performance achieved with hand-designed compact state information.

PDF Details

ICML Conference 2021 Conference Paper

State Relevance for Off-Policy Evaluation

Simon P. Shen
Yecheng Jason Ma 0001
Omer Gottesman
Finale Doshi

Importance sampling-based estimators for off-policy evaluation (OPE) are valued for their simplicity, unbiasedness, and reliance on relatively few assumptions. However, the variance of these estimators is often high, especially when trajectories are of different lengths. In this work, we introduce Omitting-States-Irrelevant-to-Return Importance Sampling (OSIRIS), an estimator which reduces variance by strategically omitting likelihood ratios associated with certain states. We formalize the conditions under which OSIRIS is unbiased and has lower variance than ordinary importance sampling, and we demonstrate these properties empirically.

Details

ICML Conference 2020 Conference Paper

Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential Transitions

Omer Gottesman
Joseph Futoma
Yao Liu 0009
Sonali Parbhoo
Leo A. Celi
Emma Brunskill
Finale Doshi

Off-policy evaluation in reinforcement learning offers the chance of using observational data to improve future outcomes in domains such as healthcare and education, but safe deployment in high stakes settings requires ways of assessing its validity. Traditional measures such as confidence intervals may be insufficient due to noise, limited data and confounding. In this paper we develop a method that could serve as a hybrid human-AI system, to enable human experts to analyze the validity of policy evaluation estimates. This is accomplished by highlighting observations in the data whose removal will have a large effect on the OPE estimate, and formulating a set of rules for choosing which ones to present to domain experts for validation. We develop methods to compute exactly the influence functions for fitted Q-evaluation with two different function classes: kernel-based and linear least squares, as well as importance sampling methods. Experiments on medical simulations and real-world intensive care unit data demonstrate that our method can be used to identify limitations in the evaluation process and make evaluation more robust.

Details

NeurIPS Conference 2020 Conference Paper

Learning to search efficiently for causally near-optimal treatments

Samuel Håkansson
Viktor Lindblom
Omer Gottesman
Fredrik D. Johansson

Finding an effective medical treatment often requires a search by trial and error. Making this search more efficient by minimizing the number of unnecessary trials could lower both costs and patient suffering. We formalize this problem as learning a policy for finding a near-optimal treatment in a minimum number of trials using a causal inference framework. We give a model-based dynamic programming algorithm which learns from observational data while being robust to unmeasured confounding. To reduce time complexity, we suggest a greedy algorithm which bounds the near-optimality constraint. The methods are evaluated on synthetic and real-world healthcare data and compared to model-free reinforcement learning. We find that our methods compare favorably to the model-free baseline while offering a more transparent trade-off between search time and treatment efficacy.

PDF Details

ICML Conference 2019 Conference Paper

Combining parametric and nonparametric models for off-policy evaluation

Omer Gottesman
Yao Liu 0009
Scott Sussex
Emma Brunskill
Finale Doshi

We consider a model-based approach to perform batch off-policy evaluation in reinforcement learning. Our method takes a mixture-of-experts approach to combine parametric and non-parametric models of the environment such that the final value estimate has the least expected error. We do so by first estimating the local accuracy of each model and then using a planner to select which model to use at every time step as to minimize the return error estimate along entire trajectories. Across a variety of domains, our mixture-based approach outperforms the individual models alone as well as state-of-the-art importance sampling-based estimators.

Details

NeurIPS Conference 2018 Conference Paper

Representation Balancing MDPs for Off-policy Policy Evaluation

Yao Liu
Omer Gottesman
Aniruddh Raghu
Matthieu Komorowski
Aldo Faisal
Finale Doshi-Velez
Emma Brunskill

We study the problem of off-policy policy evaluation (OPPE) in RL. In contrast to prior work, we consider how to estimate both the individual policy value and average policy value accurately. We draw inspiration from recent work in causal reasoning, and propose a new finite sample generalization error bound for value estimates from MDP models. Using this upper bound as an objective, we develop a learning algorithm of an MDP model with a balanced representation, and show that our approach can yield substantially lower MSE in common synthetic benchmarks and a HIV treatment simulation domain.

PDF Details