Timezone: »
Model-based reinforcement learning (RL) algorithms, which learn a dynamics model from logged experience and perform conservative planning under the learned model, have emerged as a promising paradigm for offline reinforcement learning (offline RL). However, practical variants of such model-based algorithms rely on explicit uncertainty quantification for incorporating conservatism. Uncertainty estimation with complex models, such as deep neural networks, can be difficult and unreliable. We empirically find that uncertainty estimation is not accurate and leads to poor performance in certain scenarios in offline model-based RL. We overcome this limitation by developing a new model-based offline RL algorithm, COMBO, that trains a value function using both the offline dataset and data generated using rollouts under the model while also additionally regularizing the value function on out-of-support state-action tuples generated via model rollouts. This results in a conservative estimate of the value function for out-of-support state-action tuples, without requiring explicit uncertainty estimation. Theoretically, we show that COMBO satisfies a policy improvement guarantee in the offline setting. Through extensive experiments, we find that COMBO attains greater performance compared to prior offline RL on problems that demand generalization to related but previously unseen tasks, and also consistently matches or outperforms prior offline RL methods on widely studied offline RL benchmarks, including image-based tasks.
Author Information
Tianhe Yu (Stanford University)
Aviral Kumar (UC Berkeley)
Rafael Rafailov (Stanford University)
Aravind Rajeswaran (FAIR / Facebook AI Research)
Sergey Levine (UC Berkeley)
Chelsea Finn (Stanford)
More from the Same Authors
-
2021 Spotlight: Robust Predictable Control »
Ben Eysenbach · Russ Salakhutdinov · Sergey Levine -
2021 Spotlight: Offline Reinforcement Learning as One Big Sequence Modeling Problem »
Michael Janner · Qiyang Li · Sergey Levine -
2021 Spotlight: Efficiently Identifying Task Groupings for Multi-Task Learning »
Chris Fifty · Ehsan Amid · Zhe Zhao · Tianhe Yu · Rohan Anil · Chelsea Finn -
2021 Spotlight: Pragmatic Image Compression for Human-in-the-Loop Decision-Making »
Sid Reddy · Anca Dragan · Sergey Levine -
2021 : MESA: Offline Meta-RL for Safe Adaptation and Fault Tolerance »
Michael Luo · Ashwin Balakrishna · Brijen Thananjeyan · Suraj Nair · Julian Ibarz · Jie Tan · Chelsea Finn · Ion Stoica · Ken Goldberg -
2021 : Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasets »
Frederik Ebert · Yanlai Yang · Karl Schmeckpeper · Bernadette Bucher · Kostas Daniilidis · Chelsea Finn · Sergey Levine -
2021 : Lifelong Robotic Reinforcement Learning by Retaining Experiences »
Annie Xie · Chelsea Finn -
2021 : Correct-N-Contrast: A Contrastive Approach for Improving Robustness to Spurious Correlations »
Michael Zhang · Nimit Sohoni · Hongyang Zhang · Chelsea Finn · Christopher Ré -
2021 : Extending the WILDS Benchmark for Unsupervised Adaptation »
Shiori Sagawa · Pang Wei Koh · Tony Lee · Irena Gao · Sang Michael Xie · Kendrick Shen · Ananya Kumar · Weihua Hu · Michihiro Yasunaga · Henrik Marklund · Sara Beery · Ian Stavness · Jure Leskovec · Kate Saenko · Tatsunori Hashimoto · Sergey Levine · Chelsea Finn · Percy Liang -
2021 : Test Time Robustification of Deep Models via Adaptation and Augmentation »
Marvin Zhang · Sergey Levine · Chelsea Finn -
2021 : The Reflective Explorer: Online Meta-Exploration from Offline Data in Realistic Robotic Tasks »
Rafael Rafailov · · Tianhe Yu · Avi Singh · Mariano Phielipp · Chelsea Finn -
2021 : Value Function Spaces: Skill-Centric State Abstractions for Long-Horizon Reasoning »
· Ted Xiao · Alexander Toshev · Sergey Levine · brian ichter -
2021 : Data Sharing without Rewards in Multi-Task Offline Reinforcement Learning »
Tianhe Yu · Aviral Kumar · Yevgen Chebotar · Chelsea Finn · Sergey Levine · Karol Hausman -
2021 : Should I Run Offline Reinforcement Learning or Behavioral Cloning? »
Aviral Kumar · Joey Hong · Anikait Singh · Sergey Levine -
2021 : DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization »
Aviral Kumar · Rishabh Agarwal · Tengyu Ma · Aaron Courville · George Tucker · Sergey Levine -
2021 : CIC: Contrastive Intrinsic Control for Unsupervised Skill Discovery »
Misha Laskin · Hao Liu · Xue Bin Peng · Denis Yarats · Aravind Rajeswaran · Pieter Abbeel -
2021 : Offline Reinforcement Learning with In-sample Q-Learning »
Ilya Kostrikov · Ashvin Nair · Sergey Levine -
2021 : C-Planning: An Automatic Curriculum for Learning Goal-Reaching Tasks »
Tianjun Zhang · Ben Eysenbach · Russ Salakhutdinov · Sergey Levine · Joseph Gonzalez -
2021 : The Information Geometry of Unsupervised Reinforcement Learning »
Ben Eysenbach · Russ Salakhutdinov · Sergey Levine -
2021 : Mismatched No More: Joint Model-Policy Optimization for Model-Based RL »
Ben Eysenbach · Alexander Khazatsky · Sergey Levine · Russ Salakhutdinov -
2021 : Offline Meta-Reinforcement Learning with Online Self-Supervision »
Vitchyr Pong · Ashvin Nair · Laura Smith · Catherine Huang · Sergey Levine -
2021 : Hybrid Imitative Planning with Geometric and Predictive Costs in Offroad Environments »
Daniel Shin · · Ali Agha · Nicholas Rhinehart · Sergey Levine -
2021 : CoMPS: Continual Meta Policy Search »
Glen Berseth · Zhiwei Zhang · Grace Zhang · Chelsea Finn · Sergey Levine -
2021 : Behavioral Priors and Dynamics Models: Improving Performance and Domain Transfer in Offline RL »
Catherine Cang · Aravind Rajeswaran · Pieter Abbeel · Misha Laskin -
2021 : Discriminator Augmented Model-Based Reinforcement Learning »
Allan Zhou · Archit Sharma · Chelsea Finn -
2021 : Curiosity with Chelsea Finn, Celeste Kidd, Timothy Verstynen »
Celeste Kidd · Chelsea Finn · Timothy Verstynen · Johnathan Flowers -
2021 : Example-Based Offline Reinforcement Learning without Rewards »
Kyle Hatch · Tianhe Yu · Rafael Rafailov · Chelsea Finn -
2021 : The Reflective Explorer: Online Meta-Exploration from Offline Data in Realistic Robotic Tasks »
Rafael Rafailov · · Tianhe Yu · Avi Singh · Mariano Phielipp · Chelsea Finn -
2021 : Lifelong Robotic Reinforcement Learning by Retaining Experiences »
Annie Xie · Chelsea Finn -
2021 : Speaker Intro »
Aviral Kumar · George Tucker -
2021 : Speaker Intro »
Aviral Kumar · George Tucker -
2021 : Speaker Intro »
Rishabh Agarwal · Aviral Kumar -
2021 : Speaker Intro »
Rishabh Agarwal · Aviral Kumar -
2021 Workshop: Offline Reinforcement Learning »
Rishabh Agarwal · Aviral Kumar · George Tucker · Justin Fu · Nan Jiang · Doina Precup · Aviral Kumar -
2021 : Opening Remarks »
Rishabh Agarwal · Aviral Kumar -
2021 : Discussion: Chelsea Finn, Masashi Sugiyama »
Chelsea Finn · Masashi Sugiyama -
2021 : Robustness through the Lens of Invariance »
Chelsea Finn -
2021 : Offline Meta-Reinforcement Learning with Online Self-Supervision Q&A »
Vitchyr Pong · Ashvin Nair · Laura Smith · Catherine Huang · Sergey Levine -
2021 : Offline Meta-Reinforcement Learning with Online Self-Supervision »
Vitchyr Pong · Ashvin Nair · Laura Smith · Catherine Huang · Sergey Levine -
2021 : Offline Meta-Reinforcement Learning with Online Self-Supervision »
Vitchyr Pong · Ashvin Nair · Laura Smith · Catherine Huang · Sergey Levine -
2021 : DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization Q&A »
Aviral Kumar · Rishabh Agarwal · Tengyu Ma · Aaron Courville · George Tucker · Sergey Levine -
2021 : DR3: Value-Based Deep Reinforcement Learning Requires Explicit Regularization »
Aviral Kumar · Rishabh Agarwal · Tengyu Ma · Aaron Courville · George Tucker · Sergey Levine -
2021 Workshop: Deep Reinforcement Learning »
Pieter Abbeel · Chelsea Finn · David Silver · Matthew Taylor · Martha White · Srijita Das · Yuqing Du · Andrew Patterson · Manan Tomar · Olivia Watkins -
2021 Oral: Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification »
Ben Eysenbach · Sergey Levine · Russ Salakhutdinov -
2021 Poster: Visual Adversarial Imitation Learning using Variational Models »
Rafael Rafailov · Tianhe Yu · Aravind Rajeswaran · Chelsea Finn -
2021 Poster: Robust Predictable Control »
Ben Eysenbach · Russ Salakhutdinov · Sergey Levine -
2021 Poster: Efficiently Identifying Task Groupings for Multi-Task Learning »
Chris Fifty · Ehsan Amid · Zhe Zhao · Tianhe Yu · Rohan Anil · Chelsea Finn -
2021 Poster: Which Mutual-Information Representation Learning Objectives are Sufficient for Control? »
Kate Rakelly · Abhishek Gupta · Carlos Florensa · Sergey Levine -
2021 Poster: Outcome-Driven Reinforcement Learning via Variational Inference »
Tim G. J. Rudner · Vitchyr Pong · Rowan McAllister · Yarin Gal · Sergey Levine -
2021 Poster: Decision Transformer: Reinforcement Learning via Sequence Modeling »
Lili Chen · Kevin Lu · Aravind Rajeswaran · Kimin Lee · Aditya Grover · Misha Laskin · Pieter Abbeel · Aravind Srinivas · Igor Mordatch -
2021 Poster: Bayesian Adaptation for Covariate Shift »
Aurick Zhou · Sergey Levine -
2021 Poster: Offline Reinforcement Learning as One Big Sequence Modeling Problem »
Michael Janner · Qiyang Li · Sergey Levine -
2021 Poster: Pragmatic Image Compression for Human-in-the-Loop Decision-Making »
Sid Reddy · Anca Dragan · Sergey Levine -
2021 Poster: Replacing Rewards with Examples: Example-Based Policy Search via Recursive Classification »
Ben Eysenbach · Sergey Levine · Russ Salakhutdinov -
2021 Poster: Information is Power: Intrinsic Control via Information Capture »
Nicholas Rhinehart · Jenny Wang · Glen Berseth · John Co-Reyes · Danijar Hafner · Chelsea Finn · Sergey Levine -
2021 Poster: Conservative Data Sharing for Multi-Task Offline Reinforcement Learning »
Tianhe Yu · Aviral Kumar · Yevgen Chebotar · Karol Hausman · Sergey Levine · Chelsea Finn -
2021 Poster: Meta-learning with an Adaptive Task Scheduler »
Huaxiu Yao · Yu Wang · Ying Wei · Peilin Zhao · Mehrdad Mahdavi · Defu Lian · Chelsea Finn -
2021 Poster: Reinforcement Learning with Latent Flow »
Wenling Shang · Xiaofei Wang · Aravind Srinivas · Aravind Rajeswaran · Yang Gao · Pieter Abbeel · Misha Laskin -
2021 Poster: Noether Networks: meta-learning useful conserved quantities »
Ferran Alet · Dylan Doblar · Allan Zhou · Josh Tenenbaum · Kenji Kawaguchi · Chelsea Finn -
2021 Poster: Why Generalization in RL is Difficult: Epistemic POMDPs and Implicit Partial Observability »
Dibya Ghosh · Jad Rahme · Aviral Kumar · Amy Zhang · Ryan Adams · Sergey Levine -
2021 Poster: Differentiable Annealed Importance Sampling and the Perils of Gradient Noise »
Guodong Zhang · Kyle Hsu · Jianing Li · Chelsea Finn · Roger Grosse -
2021 Poster: Autonomous Reinforcement Learning via Subgoal Curricula »
Archit Sharma · Abhishek Gupta · Sergey Levine · Karol Hausman · Chelsea Finn -
2021 Poster: Adaptive Risk Minimization: Learning to Adapt to Domain Shift »
Marvin Zhang · Henrik Marklund · Nikita Dhawan · Abhishek Gupta · Sergey Levine · Chelsea Finn -
2020 : Design-Bench: Benchmarks for Data-Driven Offline Model-Based Optimization »
Brandon Trabucco · Aviral Kumar · XINYANG GENG · Sergey Levine -
2020 : Conservative Objective Models: A Simple Approach to Effective Model-Based Optimization »
Brandon Trabucco · Aviral Kumar · XINYANG GENG · Sergey Levine -
2020 : Panel Discussion & Closing »
Yejin Choi · Alexei Efros · Chelsea Finn · Kristen Grauman · Quoc V Le · Yann LeCun · Ruslan Salakhutdinov · Eric Xing -
2020 : QA: Chelsea Finn »
Chelsea Finn -
2020 : Mini-panel discussion 3 - Prioritizing Real World RL Challenges »
Chelsea Finn · Thomas Dietterich · Angela Schoellig · Anca Dragan · Anusha Nagabandi · Doina Precup -
2020 : Invited Talk: Chelsea Finn »
Chelsea Finn -
2020 : Keynote: Chelsea Finn »
Chelsea Finn -
2020 : Panel »
Emma Brunskill · Nan Jiang · Nando de Freitas · Finale Doshi-Velez · Sergey Levine · John Langford · Lihong Li · George Tucker · Rishabh Agarwal · Aviral Kumar -
2020 Workshop: Offline Reinforcement Learning »
Aviral Kumar · Rishabh Agarwal · George Tucker · Lihong Li · Doina Precup · Aviral Kumar -
2020 : Introduction »
Aviral Kumar · George Tucker · Rishabh Agarwal -
2020 : Invited talk - Underfitting and Uncertainty in Self-Supervised Predictive Models »
Chelsea Finn -
2020 Workshop: Deep Reinforcement Learning »
Pieter Abbeel · Chelsea Finn · Joelle Pineau · David Silver · Satinder Singh · Coline Devin · Misha Laskin · Kimin Lee · Janarthanan Rajendran · Vivek Veeriah -
2020 Workshop: Object Representations for Learning and Reasoning »
William Agnew · Rim Assouel · Michael Chang · Antonia Creswell · Eliza Kosoy · Aravind Rajeswaran · Sjoerd van Steenkiste -
2020 Poster: Weakly-Supervised Reinforcement Learning for Controllable Behavior »
Lisa Lee · Benjamin Eysenbach · Russ Salakhutdinov · Shixiang (Shane) Gu · Chelsea Finn -
2020 Poster: Continual Learning of Control Primitives : Skill Discovery via Reset-Games »
Kelvin Xu · Siddharth Verma · Chelsea Finn · Sergey Levine -
2020 Poster: Gradient Surgery for Multi-Task Learning »
Tianhe Yu · Saurabh Kumar · Abhishek Gupta · Sergey Levine · Karol Hausman · Chelsea Finn -
2020 Poster: Continuous Meta-Learning without Tasks »
James Harrison · Apoorva Sharma · Chelsea Finn · Marco Pavone -
2020 Poster: One Solution is Not All You Need: Few-Shot Extrapolation via Structured MaxEnt RL »
Saurabh Kumar · Aviral Kumar · Sergey Levine · Chelsea Finn -
2020 Poster: Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors »
Karl Pertsch · Oleh Rybkin · Frederik Ebert · Shenghao Zhou · Dinesh Jayaraman · Chelsea Finn · Sergey Levine -
2020 Poster: MOPO: Model-based Offline Policy Optimization »
Tianhe Yu · Garrett Thomas · Lantao Yu · Stefano Ermon · James Zou · Sergey Levine · Chelsea Finn · Tengyu Ma -
2020 Tutorial: (Track3) Offline Reinforcement Learning: From Algorithm Design to Practical Applications »
Sergey Levine · Aviral Kumar -
2019 : Poster Presentations »
Rahul Mehta · Andrew Lampinen · Binghong Chen · Sergio Pascual-Diaz · Jordi Grau-Moya · Aldo Faisal · Jonathan Tompson · Yiren Lu · Khimya Khetarpal · Martin Klissarov · Pierre-Luc Bacon · Doina Precup · Thanard Kurutach · Aviv Tamar · Pieter Abbeel · Jinke He · Maximilian Igl · Shimon Whiteson · Wendelin Boehmer · Raphaël Marinier · Olivier Pietquin · Karol Hausman · Sergey Levine · Chelsea Finn · Tianhe Yu · Lisa Lee · Benjamin Eysenbach · Emilio Parisotto · Eric Xing · Ruslan Salakhutdinov · Hongyu Ren · Anima Anandkumar · Deepak Pathak · Christopher Lu · Trevor Darrell · Alexei Efros · Phillip Isola · Feng Liu · Bo Han · Gang Niu · Masashi Sugiyama · Saurabh Kumar · Janith Petangoda · Johan Ferret · James McClelland · Kara Liu · Animesh Garg · Robert Lange -
2019 Workshop: Learning with Rich Experience: Integration of Learning Paradigms »
Zhiting Hu · Andrew Wilson · Chelsea Finn · Lisa Lee · Taylor Berg-Kirkpatrick · Ruslan Salakhutdinov · Eric Xing -
2019 Poster: Graph Normalizing Flows »
Jenny Liu · Aviral Kumar · Jimmy Ba · Jamie Kiros · Kevin Swersky -
2019 Poster: Language as an Abstraction for Hierarchical Deep Reinforcement Learning »
YiDing Jiang · Shixiang (Shane) Gu · Kevin Murphy · Chelsea Finn -
2018 : Spotlights »
Guangneng Hu · Ke Li · Aviral Kumar · Phi Vu Tran · Samuel Fadel · Rita Kuznetsova · Bong-Nam Kang · Behrouz Haji Soleimani · Jinwon An · Nathan de Lara · Anjishnu Kumar · Tillman Weyde · Melanie Weber · Kristen Altenburger · Saeed Amizadeh · Xiaoran Xu · Yatin Nandwani · Yang Guo · Maria Pacheco · William Fedus · Guillaume Jaume · Yuka Yoneda · Yunpu Ma · Yunsheng Bai · Berk Kapicioglu · Maximilian Nickel · Fragkiskos Malliaros · Beier Zhu · Aleksandar Bojchevski · Joshua Joseph · Gemma Roig · Esma Balkir · Xander Steenbrugge -
2017 Demonstration: Deep Robotic Learning using Visual Imagination and Meta-Learning »
Chelsea Finn · Frederik Ebert · Tianhe Yu · Annie Xie · Sudeep Dasari · Pieter Abbeel · Sergey Levine -
2017 Poster: Towards Generalization and Simplicity in Continuous Control »
Aravind Rajeswaran · Kendall Lowrey · Emanuel Todorov · Sham Kakade