Timezone: »
Offline RL algorithms must account for the fact that the dataset they are provided may leave many facets of the environment unknown. The most common way to approach this challenge is to employ pessimistic or conservative methods, which avoid behaviors that are too dissimilar from those in the training dataset. However, relying exclusively on conservatism has drawbacks: performance is sensitive to the exact degree of conservatism, and conservative objectives can recover highly suboptimal policies. In this work, we propose that offline RL methods should instead be adaptive in the presence of uncertainty. We show that acting optimally in offline RL in a Bayesian sense involves solving an implicit POMDP. As a result, optimal policies for offline RL must be adaptive, depending not just on the current state but rather all the transitions seen so far during evaluation. We present a model-free algorithm for approximating this optimal adaptive policy, and demonstrate the efficacy of learning such adaptive policies in offline RL benchmarks.
Author Information
Dibya Ghosh (UC Berkeley)
Anurag Ajay (MIT)
Pulkit Agrawal (MIT)
Sergey Levine (UC Berkeley)

Sergey Levine received a BS and MS in Computer Science from Stanford University in 2009, and a Ph.D. in Computer Science from Stanford University in 2014. He joined the faculty of the Department of Electrical Engineering and Computer Sciences at UC Berkeley in fall 2016. His work focuses on machine learning for decision making and control, with an emphasis on deep learning and reinforcement learning algorithms. Applications of his work include autonomous robots and vehicles, as well as computer vision and graphics. His research includes developing algorithms for end-to-end training of deep neural network policies that combine perception and control, scalable algorithms for inverse reinforcement learning, deep reinforcement learning algorithms, and more.
Related Events (a corresponding poster, oral, or spotlight)
-
2022 Poster: Offline RL Policies Should Be Trained to be Adaptive »
Tue. Jul 19th through Wed the 20th Room Hall E #838
More from the Same Authors
-
2020 : Learning Action Priors for Visuomotor transfer »
Anurag Ajay -
2021 : Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability »
Dibya Ghosh · Jad Rahme · Aviral Kumar · Amy Zhang · Ryan P. Adams · Sergey Levine -
2021 : Topological Experience Replay for Fast Q-Learning »
Zhang-Wei Hong · Tao Chen · Yen-Chen Lin · Joni Pajarinen · Pulkit Agrawal -
2021 : Value-Based Deep Reinforcement Learning Requires Explicit Regularization »
Aviral Kumar · Rishabh Agarwal · Aaron Courville · Tengyu Ma · George Tucker · Sergey Levine -
2021 : Multi-Task Offline Reinforcement Learning with Conservative Data Sharing »
Tianhe (Kevin) Yu · Aviral Kumar · Yevgen Chebotar · Karol Hausman · Sergey Levine · Chelsea Finn -
2021 : Reinforcement Learning as One Big Sequence Modeling Problem »
Michael Janner · Qiyang Li · Sergey Levine -
2021 : ReLMM: Practical RL for Learning Mobile Manipulation Skills Using Only Onboard Sensors »
Charles Sun · Jedrzej Orbik · Coline Devin · Abhishek Gupta · Glen Berseth · Sergey Levine -
2021 : Topological Experience Replay for Fast Q-Learning »
Zhang-Wei Hong · Tao Chen · Yen-Chen Lin · Joni Pajarinen · Pulkit Agrawal -
2021 : Understanding the Generalization Gap in Visual Reinforcement Learning »
Anurag Ajay · Ge Yang · Ofir Nachum · Pulkit Agrawal -
2021 : Multi-Task Offline Reinforcement Learning with Conservative Data Sharing »
Tianhe (Kevin) Yu · Aviral Kumar · Yevgen Chebotar · Karol Hausman · Sergey Levine · Chelsea Finn -
2021 : Value-Based Deep Reinforcement Learning Requires Explicit Regularization »
Aviral Kumar · Rishabh Agarwal · Aaron Courville · Tengyu Ma · George Tucker · Sergey Levine -
2021 : Value-Based Deep Reinforcement Learning Requires Explicit Regularization »
Aviral Kumar · Rishabh Agarwal · Aaron Courville · Tengyu Ma · George Tucker · Sergey Levine -
2022 : Distributionally Adaptive Meta Reinforcement Learning »
Anurag Ajay · Dibya Ghosh · Sergey Levine · Pulkit Agrawal · Abhishek Gupta -
2022 : Distributionally Adaptive Meta Reinforcement Learning »
Anurag Ajay · Dibya Ghosh · Sergey Levine · Pulkit Agrawal · Abhishek Gupta -
2023 : Visual Dexterity: In-hand Dexterous Manipulation from Depth »
Tao Chen · Megha Tippur · Siyang Wu · Vikash Kumar · Edward Adelson · Pulkit Agrawal -
2023 : Offline Goal-Conditioned RL with Latent States as Actions »
Seohong Park · Dibya Ghosh · Benjamin Eysenbach · Sergey Levine -
2023 : Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-loop feedback »
Marcel Torne Villasevil · Max Balsells I Pamies · Zihan Wang · Samedh Desai · Tao Chen · Pulkit Agrawal · Abhishek Gupta -
2023 : Video-Guided Skill Discovery »
Manan Tomar · Dibya Ghosh · Vivek Myers · Anca Dragan · Matthew Taylor · Philip Bachman · Sergey Levine -
2023 Poster: Parallel $Q$-Learning: Scaling Off-policy Reinforcement Learning under Massively Parallel Simulation »
Zechu Li · Tao Chen · Zhang-Wei Hong · Anurag Ajay · Pulkit Agrawal -
2023 Poster: Diagnosis, Feedback, Adaptation: A Human-in-the-Loop Framework for Test-Time Policy Adaptation »
Andi Peng · Aviv Netanyahu · Mark Ho · Tianmin Shu · Andreea Bobu · Julie Shah · Pulkit Agrawal -
2023 Poster: Statistical Learning under Heterogenous Distribution Shift »
Max Simchowitz · Anurag Ajay · Pulkit Agrawal · Akshay Krishnamurthy -
2023 Poster: Reinforcement Learning from Passive Data via Latent Intentions »
Dibya Ghosh · Chethan Bhateja · Sergey Levine -
2023 Poster: Straightening Out the Straight-Through Estimator: Overcoming Optimization Challenges in Vector Quantized Networks »
Minyoung Huh · Brian Cheung · Pulkit Agrawal · Phillip Isola -
2023 Oral: Reinforcement Learning from Passive Data via Latent Intentions »
Dibya Ghosh · Chethan Bhateja · Sergey Levine -
2023 Poster: TGRL: An Algorithm for Teacher Guided Reinforcement Learning »
Idan Shenfeld · Zhang-Wei Hong · Aviv Tamar · Pulkit Agrawal -
2022 : Q/A Sergey Levine »
Sergey Levine -
2022 : Invited Speaker: Sergey Levine »
Sergey Levine -
2022 Poster: Offline Meta-Reinforcement Learning with Online Self-Supervision »
Vitchyr Pong · Ashvin Nair · Laura Smith · Catherine Huang · Sergey Levine -
2022 Poster: Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization »
Brandon Trabucco · Xinyang Geng · Aviral Kumar · Sergey Levine -
2022 Poster: How to Leverage Unlabeled Data in Offline Reinforcement Learning »
Tianhe (Kevin) Yu · Aviral Kumar · Yevgen Chebotar · Karol Hausman · Chelsea Finn · Sergey Levine -
2022 Poster: Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning »
Aviv Netanyahu · Tianmin Shu · Josh Tenenbaum · Pulkit Agrawal -
2022 Spotlight: How to Leverage Unlabeled Data in Offline Reinforcement Learning »
Tianhe (Kevin) Yu · Aviral Kumar · Yevgen Chebotar · Karol Hausman · Chelsea Finn · Sergey Levine -
2022 Spotlight: Discovering Generalizable Spatial Goal Representations via Graph-based Active Reward Learning »
Aviv Netanyahu · Tianmin Shu · Josh Tenenbaum · Pulkit Agrawal -
2022 Spotlight: Offline Meta-Reinforcement Learning with Online Self-Supervision »
Vitchyr Pong · Ashvin Nair · Laura Smith · Catherine Huang · Sergey Levine -
2022 Spotlight: Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization »
Brandon Trabucco · Xinyang Geng · Aviral Kumar · Sergey Levine -
2022 Poster: Planning with Diffusion for Flexible Behavior Synthesis »
Michael Janner · Yilun Du · Josh Tenenbaum · Sergey Levine -
2022 Oral: Planning with Diffusion for Flexible Behavior Synthesis »
Michael Janner · Yilun Du · Josh Tenenbaum · Sergey Levine -
2021 : Value-Based Deep Reinforcement Learning Requires Explicit Regularization »
Aviral Kumar · Rishabh Agarwal · Aaron Courville · Tengyu Ma · George Tucker · Sergey Levine -
2021 Workshop: Self-Supervised Learning for Reasoning and Perception »
Pengtao Xie · Shanghang Zhang · Ishan Misra · Pulkit Agrawal · Katerina Fragkiadaki · Ruisi Zhang · Tassilo Klein · Asli Celikyilmaz · Mihaela van der Schaar · Eric Xing -
2021 Poster: Simple and Effective VAE Training with Calibrated Decoders »
Oleh Rybkin · Kostas Daniilidis · Sergey Levine -
2021 Poster: WILDS: A Benchmark of in-the-Wild Distribution Shifts »
Pang Wei Koh · Shiori Sagawa · Henrik Marklund · Sang Michael Xie · Marvin Zhang · Akshay Balsubramani · Weihua Hu · Michihiro Yasunaga · Richard Lanas Phillips · Irena Gao · Tony Lee · Etienne David · Ian Stavness · Wei Guo · Berton Earnshaw · Imran Haque · Sara Beery · Jure Leskovec · Anshul Kundaje · Emma Pierson · Sergey Levine · Chelsea Finn · Percy Liang -
2021 Oral: WILDS: A Benchmark of in-the-Wild Distribution Shifts »
Pang Wei Koh · Shiori Sagawa · Henrik Marklund · Sang Michael Xie · Marvin Zhang · Akshay Balsubramani · Weihua Hu · Michihiro Yasunaga · Richard Lanas Phillips · Irena Gao · Tony Lee · Etienne David · Ian Stavness · Wei Guo · Berton Earnshaw · Imran Haque · Sara Beery · Jure Leskovec · Anshul Kundaje · Emma Pierson · Sergey Levine · Chelsea Finn · Percy Liang -
2021 Spotlight: Simple and Effective VAE Training with Calibrated Decoders »
Oleh Rybkin · Kostas Daniilidis · Sergey Levine -
2021 Social: RL Social »
Dibya Ghosh · Hager Radi · Derek Li · Alex Ayoub · Erfan Miahi · Rishabh Agarwal · Charline Le Lan · Abhishek Naik · John D. Martin · Shruti Mishra · Adrien Ali Taiga -
2021 Poster: Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment »
Michael Chang · Sid Kaushik · Sergey Levine · Thomas Griffiths -
2021 Poster: Conservative Objective Models for Effective Offline Model-Based Optimization »
Brandon Trabucco · Aviral Kumar · Xinyang Geng · Sergey Levine -
2021 Spotlight: Conservative Objective Models for Effective Offline Model-Based Optimization »
Brandon Trabucco · Aviral Kumar · Xinyang Geng · Sergey Levine -
2021 Oral: Modularity in Reinforcement Learning via Algorithmic Independence in Credit Assignment »
Michael Chang · Sid Kaushik · Sergey Levine · Thomas Griffiths -
2021 Poster: Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning »
Hiroki Furuta · Tatsuya Matsushima · Tadashi Kozuno · Yutaka Matsuo · Sergey Levine · Ofir Nachum · Shixiang Gu -
2021 Poster: MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning »
Kevin Li · Abhishek Gupta · Ashwin D Reddy · Vitchyr Pong · Aurick Zhou · Justin Yu · Sergey Levine -
2021 Poster: PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning »
Angelos Filos · Clare Lyle · Yarin Gal · Sergey Levine · Natasha Jaques · Gregory Farquhar -
2021 Spotlight: MURAL: Meta-Learning Uncertainty-Aware Rewards for Outcome-Driven Reinforcement Learning »
Kevin Li · Abhishek Gupta · Ashwin D Reddy · Vitchyr Pong · Aurick Zhou · Justin Yu · Sergey Levine -
2021 Spotlight: Policy Information Capacity: Information-Theoretic Measure for Task Complexity in Deep Reinforcement Learning »
Hiroki Furuta · Tatsuya Matsushima · Tadashi Kozuno · Yutaka Matsuo · Sergey Levine · Ofir Nachum · Shixiang Gu -
2021 Oral: PsiPhi-Learning: Reinforcement Learning with Demonstrations using Successor Features and Inverse Temporal Difference Learning »
Angelos Filos · Clare Lyle · Yarin Gal · Sergey Levine · Natasha Jaques · Gregory Farquhar -
2021 Poster: Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation »
Aurick Zhou · Sergey Levine -
2021 Poster: Learning Task Informed Abstractions »
Xiang Fu · Ge Yang · Pulkit Agrawal · Tommi Jaakkola -
2021 Poster: Model-Based Reinforcement Learning via Latent-Space Collocation »
Oleh Rybkin · Chuning Zhu · Anusha Nagabandi · Kostas Daniilidis · Igor Mordatch · Sergey Levine -
2021 Spotlight: Model-Based Reinforcement Learning via Latent-Space Collocation »
Oleh Rybkin · Chuning Zhu · Anusha Nagabandi · Kostas Daniilidis · Igor Mordatch · Sergey Levine -
2021 Spotlight: Amortized Conditional Normalized Maximum Likelihood: Reliable Out of Distribution Uncertainty Estimation »
Aurick Zhou · Sergey Levine -
2021 Spotlight: Learning Task Informed Abstractions »
Xiang Fu · Ge Yang · Pulkit Agrawal · Tommi Jaakkola -
2020 : Invited Talk 9: Prof. Sergey Levine from UC Berkeley »
Sergey Levine -
2020 Poster: Decentralized Reinforcement Learning: Global Decision-Making via Local Economic Transactions »
Michael Chang · Sid Kaushik · S. Matthew Weinberg · Thomas Griffiths · Sergey Levine -
2020 Poster: Learning Human Objectives by Evaluating Hypothetical Behavior »
Siddharth Reddy · Anca Dragan · Sergey Levine · Shane Legg · Jan Leike -
2020 Poster: Skew-Fit: State-Covering Self-Supervised Reinforcement Learning »
Vitchyr Pong · Murtaza Dalal · Steven Lin · Ashvin Nair · Shikhar Bahl · Sergey Levine -
2020 Poster: Can Autonomous Vehicles Identify, Recover From, and Adapt to Distribution Shifts? »
Angelos Filos · Panagiotis Tigas · Rowan McAllister · Nicholas Rhinehart · Sergey Levine · Yarin Gal -
2020 Poster: Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings »
Jesse Zhang · Brian Cheung · Chelsea Finn · Sergey Levine · Dinesh Jayaraman -
2020 Poster: Representations for Stable Off-Policy Reinforcement Learning »
Dibya Ghosh · Marc Bellemare -
2019 : Sergey Levine: "Imitation, Prediction, and Model-Based Reinforcement Learning for Autonomous Driving" »
Sergey Levine -
2019 : Sergey Levine: Unsupervised Reinforcement Learning and Meta-Learning »
Sergey Levine -
2019 Workshop: ICML Workshop on Imitation, Intent, and Interaction (I3) »
Nicholas Rhinehart · Sergey Levine · Chelsea Finn · He He · Ilya Kostrikov · Justin Fu · Siddharth Reddy -
2019 : Sergei Levine: Distribution Matching and Mutual Information in Reinforcement Learning »
Sergey Levine -
2019 Workshop: Generative Modeling and Model-Based Reasoning for Robotics and AI »
Aravind Rajeswaran · Emanuel Todorov · Igor Mordatch · William Agnew · Amy Zhang · Joelle Pineau · Michael Chang · Dumitru Erhan · Sergey Levine · Kimberly Stachenfeld · Marvin Zhang -
2019 Poster: Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables »
Kate Rakelly · Aurick Zhou · Chelsea Finn · Sergey Levine · Deirdre Quillen -
2019 Poster: SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning »
Marvin Zhang · Sharad Vikram · Laura Smith · Pieter Abbeel · Matthew Johnson · Sergey Levine -
2019 Oral: Efficient Off-Policy Meta-Reinforcement Learning via Probabilistic Context Variables »
Kate Rakelly · Aurick Zhou · Chelsea Finn · Sergey Levine · Deirdre Quillen -
2019 Oral: SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning »
Marvin Zhang · Sharad Vikram · Laura Smith · Pieter Abbeel · Matthew Johnson · Sergey Levine -
2019 Poster: Learning a Prior over Intent via Meta-Inverse Reinforcement Learning »
Kelvin Xu · Ellis Ratner · Anca Dragan · Sergey Levine · Chelsea Finn -
2019 Poster: EMI: Exploration with Mutual Information »
Hyoungseok Kim · Jaekyeom Kim · Yeonwoo Jeong · Sergey Levine · Hyun Oh Song -
2019 Poster: Online Meta-Learning »
Chelsea Finn · Aravind Rajeswaran · Sham Kakade · Sergey Levine -
2019 Poster: Diagnosing Bottlenecks in Deep Q-learning Algorithms »
Justin Fu · Aviral Kumar · Matthew Soh · Sergey Levine -
2019 Oral: Learning a Prior over Intent via Meta-Inverse Reinforcement Learning »
Kelvin Xu · Ellis Ratner · Anca Dragan · Sergey Levine · Chelsea Finn -
2019 Oral: EMI: Exploration with Mutual Information »
Hyoungseok Kim · Jaekyeom Kim · Yeonwoo Jeong · Sergey Levine · Hyun Oh Song -
2019 Oral: Diagnosing Bottlenecks in Deep Q-learning Algorithms »
Justin Fu · Aviral Kumar · Matthew Soh · Sergey Levine -
2019 Oral: Online Meta-Learning »
Chelsea Finn · Aravind Rajeswaran · Sham Kakade · Sergey Levine -
2019 Tutorial: Meta-Learning: from Few-Shot Learning to Rapid Reinforcement Learning »
Chelsea Finn · Sergey Levine -
2018 Poster: Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor »
Tuomas Haarnoja · Aurick Zhou · Pieter Abbeel · Sergey Levine -
2018 Poster: Investigating Human Priors for Playing Video Games »
Rachit Dubey · Pulkit Agrawal · Deepak Pathak · Tom Griffiths · Alexei Efros -
2018 Poster: Regret Minimization for Partially Observable Deep Reinforcement Learning »
Peter Jin · EECS Kurt Keutzer · Sergey Levine -
2018 Poster: The Mirage of Action-Dependent Baselines in Reinforcement Learning »
George Tucker · Surya Bhupatiraju · Shixiang Gu · Richard E Turner · Zoubin Ghahramani · Sergey Levine -
2018 Oral: Regret Minimization for Partially Observable Deep Reinforcement Learning »
Peter Jin · EECS Kurt Keutzer · Sergey Levine -
2018 Oral: Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor »
Tuomas Haarnoja · Aurick Zhou · Pieter Abbeel · Sergey Levine -
2018 Oral: The Mirage of Action-Dependent Baselines in Reinforcement Learning »
George Tucker · Surya Bhupatiraju · Shixiang Gu · Richard E Turner · Zoubin Ghahramani · Sergey Levine -
2018 Oral: Investigating Human Priors for Playing Video Games »
Rachit Dubey · Pulkit Agrawal · Deepak Pathak · Tom Griffiths · Alexei Efros -
2018 Poster: Latent Space Policies for Hierarchical Reinforcement Learning »
Tuomas Haarnoja · Kristian Hartikainen · Pieter Abbeel · Sergey Levine -
2018 Poster: Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings »
John Co-Reyes · Yu Xuan Liu · Abhishek Gupta · Benjamin Eysenbach · Pieter Abbeel · Sergey Levine -
2018 Poster: Universal Planning Networks: Learning Generalizable Representations for Visuomotor Control »
Aravind Srinivas · Allan Jabri · Pieter Abbeel · Sergey Levine · Chelsea Finn -
2018 Oral: Universal Planning Networks: Learning Generalizable Representations for Visuomotor Control »
Aravind Srinivas · Allan Jabri · Pieter Abbeel · Sergey Levine · Chelsea Finn -
2018 Oral: Self-Consistent Trajectory Autoencoder: Hierarchical Reinforcement Learning with Trajectory Embeddings »
John Co-Reyes · Yu Xuan Liu · Abhishek Gupta · Benjamin Eysenbach · Pieter Abbeel · Sergey Levine -
2018 Oral: Latent Space Policies for Hierarchical Reinforcement Learning »
Tuomas Haarnoja · Kristian Hartikainen · Pieter Abbeel · Sergey Levine -
2017 : Lifelong Learning - Panel Discussion »
Sergey Levine · Joelle Pineau · Balaraman Ravindran · Andrei A Rusu -
2017 : Sergey Levine: Self-supervision as a path to lifelong learning »
Sergey Levine -
2017 Poster: Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning »
Yevgen Chebotar · Karol Hausman · Marvin Zhang · Gaurav Sukhatme · Stefan Schaal · Sergey Levine -
2017 Talk: Combining Model-Based and Model-Free Updates for Trajectory-Centric Reinforcement Learning »
Yevgen Chebotar · Karol Hausman · Marvin Zhang · Gaurav Sukhatme · Stefan Schaal · Sergey Levine -
2017 Poster: Modular Multitask Reinforcement Learning with Policy Sketches »
Jacob Andreas · Dan Klein · Sergey Levine -
2017 Poster: Curiosity-driven Exploration by Self-supervised Prediction »
Deepak Pathak · Pulkit Agrawal · Alexei Efros · Trevor Darrell -
2017 Poster: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks »
Chelsea Finn · Pieter Abbeel · Sergey Levine -
2017 Poster: Reinforcement Learning with Deep Energy-Based Policies »
Tuomas Haarnoja · Haoran Tang · Pieter Abbeel · Sergey Levine -
2017 Talk: Modular Multitask Reinforcement Learning with Policy Sketches »
Jacob Andreas · Dan Klein · Sergey Levine -
2017 Talk: Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks »
Chelsea Finn · Pieter Abbeel · Sergey Levine -
2017 Talk: Curiosity-driven Exploration by Self-supervised Prediction »
Deepak Pathak · Pulkit Agrawal · Alexei Efros · Trevor Darrell -
2017 Talk: Reinforcement Learning with Deep Energy-Based Policies »
Tuomas Haarnoja · Haoran Tang · Pieter Abbeel · Sergey Levine -
2017 Tutorial: Deep Reinforcement Learning, Decision Making, and Control »
Sergey Levine · Chelsea Finn