Timezone: »
In order for humans to confidently decide where to employ RL agents for real-world tasks, a human developer must validate that the agent will perform well at test-time. Some policy interpretability methods facilitate this by capturing the policy's decision making in a set of agent rollouts. However, even the most informative trajectories of training time behavior may give little insight into the agent's behavior out of distribution. In contrast, our method conveys how the agent performs under distribution shifts by showing the agent's behavior across a wider trajectory distribution. We generate these trajectories by guiding the agent to more diverse unseen states and showing the agent's behavior there. In a user study, we demonstrate that our method enables users to score better than baseline methods on one of two agent validation tasks.
Author Information
Julius Frost (Boston University)
Olivia Watkins (UC Berkeley)
Eric Weiner (Harvey Mudd College)
Pieter Abbeel (UC Berkeley & Covariant)
Trevor Darrell (University of California at Berkeley)
Bryan Plummer (Boston University)
Kate Saenko (Boston University)
More from the Same Authors
-
2021 : Decision Transformer: Reinforcement Learning via Sequence Modeling »
Lili Chen · Kevin Lu · Aravind Rajeswaran · Kimin Lee · Aditya Grover · Michael Laskin · Pieter Abbeel · Aravind Srinivas · Igor Mordatch -
2021 : Data-Efficient Exploration with Self Play for Atari »
Michael Laskin · Catherine Cang · Ryan Rudes · Pieter Abbeel -
2021 : Hierarchical Few-Shot Imitation with Skill Transition Models »
kourosh hakhamaneshi · Ruihan Zhao · Albert Zhan · Pieter Abbeel · Michael Laskin -
2021 : Decision Transformer: Reinforcement Learning via Sequence Modeling »
Lili Chen · Kevin Lu · Aravind Rajeswaran · Kimin Lee · Aditya Grover · Michael Laskin · Pieter Abbeel · Aravind Srinivas · Igor Mordatch -
2022 : Multimodal Masked Autoencoders Learn Transferable Representations »
Xinyang Geng · Hao Liu · Lisa Lee · Dale Schuurmans · Sergey Levine · Pieter Abbeel -
2023 : ERM++: An Improved Baseline for Domain Generalization »
Piotr Teterwak · Kuniaki Saito · Theodoros Tsiligkaridis · Kate Saenko · Bryan Plummer -
2023 : LLM-grounded Text-to-Image Diffusion Models »
Long (Tony) Lian · Boyi Li · Adam Yala · Trevor Darrell -
2023 : Blockwise Parallel Transformer for Long Context Large Models »
Hao Liu · Pieter Abbeel -
2023 Poster: Masked Trajectory Models for Prediction, Representation, and Control »
Philipp Wu · Arjun Majumdar · Kevin Stone · Yixin Lin · Igor Mordatch · Pieter Abbeel · Aravind Rajeswaran -
2023 Poster: Multi-Environment Pretraining Enables Transfer to Action Limited Datasets »
David Venuto · Mengjiao Yang · Pieter Abbeel · Doina Precup · Igor Mordatch · Ofir Nachum -
2023 Poster: Guiding Pretraining in Reinforcement Learning with Large Language Models »
Yuqing Du · Olivia Watkins · Zihan Wang · Cédric Colas · Trevor Darrell · Pieter Abbeel · Abhishek Gupta · Jacob Andreas -
2023 Poster: Controllability-Aware Unsupervised Skill Discovery »
Seohong Park · Kimin Lee · Youngwoon Lee · Pieter Abbeel -
2023 Poster: Emergent Agentic Transformer from Chain of Hindsight Experience »
Hao Liu · Pieter Abbeel -
2023 Poster: Temporally Consistent Transformers for Video Generation »
Wilson Yan · Danijar Hafner · Stephen James · Pieter Abbeel -
2023 Poster: CLUTR: Curriculum Learning via Unsupervised Task Representation Learning »
Abdus Salam Azad · Izzeddin Gur · Jasper Emhoff · Nathaniel Alexis · Aleksandra Faust · Pieter Abbeel · Ion Stoica -
2023 Poster: Multi-View Masked World Models for Visual Robotic Manipulation »
Younggyo Seo · Junsu Kim · Stephen James · Kimin Lee · Jinwoo Shin · Pieter Abbeel -
2023 Poster: The Wisdom of Hindsight Makes Language Models Better Instruction Followers »
Tianjun Zhang · Fangchen Liu · Justin Wong · Pieter Abbeel · Joseph E Gonzalez -
2022 : Multimodal Masked Autoencoders Learn Transferable Representations »
Xinyang Geng · Hao Liu · Lisa Lee · Dale Schuurmans · Sergey Levine · Pieter Abbeel -
2022 : Back to the Source: Test-Time Diffusion-Driven Adaptation »
Jin Gao · Jialing Zhang · Xihui Liu · Trevor Darrell · Evan Shelhamer · Dequan Wang -
2022 Poster: Visual Attention Emerges from Recurrent Sparse Reconstruction »
Baifeng Shi · Yale Song · Neel Joshi · Trevor Darrell · Xin Wang -
2022 Poster: Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks »
Litian Liang · Yaosheng Xu · Stephen Mcaleer · Dailin Hu · Alexander Ihler · Pieter Abbeel · Roy Fox -
2022 Poster: Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents »
Wenlong Huang · Pieter Abbeel · Deepak Pathak · Igor Mordatch -
2022 Spotlight: Reducing Variance in Temporal-Difference Value Estimation via Ensemble of Deep Networks »
Litian Liang · Yaosheng Xu · Stephen Mcaleer · Dailin Hu · Alexander Ihler · Pieter Abbeel · Roy Fox -
2022 Spotlight: Visual Attention Emerges from Recurrent Sparse Reconstruction »
Baifeng Shi · Yale Song · Neel Joshi · Trevor Darrell · Xin Wang -
2022 Spotlight: Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents »
Wenlong Huang · Pieter Abbeel · Deepak Pathak · Igor Mordatch -
2022 Poster: Reinforcement Learning with Action-Free Pre-Training from Videos »
Younggyo Seo · Kimin Lee · Stephen James · Pieter Abbeel -
2022 Poster: Zero-Shot Reward Specification via Grounded Natural Language »
Parsa Mahmoudieh · Deepak Pathak · Trevor Darrell -
2022 Spotlight: Reinforcement Learning with Action-Free Pre-Training from Videos »
Younggyo Seo · Kimin Lee · Stephen James · Pieter Abbeel -
2022 Spotlight: Zero-Shot Reward Specification via Grounded Natural Language »
Parsa Mahmoudieh · Deepak Pathak · Trevor Darrell -
2021 : Poster »
Shiji Zhou · Nastaran Okati · Wichinpong Sinchaisri · Kim de Bie · Ana Lucic · Mina Khan · Ishaan Shah · JINGHUI LU · Andreas Kirsch · Julius Frost · Ze Gong · Gokul Swamy · Ah Young Kim · Ahmed Baruwa · Ranganath Krishnan -
2021 Workshop: ICML Workshop on Human in the Loop Learning (HILL) »
Trevor Darrell · Xin Wang · Li Erran Li · Fisher Yu · Zeynep Akata · Wenwu Zhu · Pradeep Ravikumar · Shiji Zhou · Shanghang Zhang · Kalesha Bullard -
2021 : Panel Discussion »
Rosemary Nan Ke · Danijar Hafner · Pieter Abbeel · Chelsea Finn · Chelsea Finn -
2021 : Invited Talk by Pieter Abbeel »
Pieter Abbeel -
2021 Poster: Decoupling Representation Learning from Reinforcement Learning »
Adam Stooke · Kimin Lee · Pieter Abbeel · Michael Laskin -
2021 Spotlight: Decoupling Representation Learning from Reinforcement Learning »
Adam Stooke · Kimin Lee · Pieter Abbeel · Michael Laskin -
2021 Poster: APS: Active Pretraining with Successor Features »
Hao Liu · Pieter Abbeel -
2021 Poster: SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning »
Kimin Lee · Michael Laskin · Aravind Srinivas · Pieter Abbeel -
2021 Spotlight: SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning »
Kimin Lee · Michael Laskin · Aravind Srinivas · Pieter Abbeel -
2021 Oral: APS: Active Pretraining with Successor Features »
Hao Liu · Pieter Abbeel -
2021 Poster: PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training »
Kimin Lee · Laura Smith · Pieter Abbeel -
2021 Poster: Compositional Video Synthesis with Action Graphs »
Amir Bar · Roi Herzig · Xiaolong Wang · Anna Rohrbach · Gal Chechik · Trevor Darrell · Amir Globerson -
2021 Spotlight: Compositional Video Synthesis with Action Graphs »
Amir Bar · Roi Herzig · Xiaolong Wang · Anna Rohrbach · Gal Chechik · Trevor Darrell · Amir Globerson -
2021 Oral: PEBBLE: Feedback-Efficient Interactive Reinforcement Learning via Relabeling Experience and Unsupervised Pre-training »
Kimin Lee · Laura Smith · Pieter Abbeel -
2021 Poster: Unsupervised Learning of Visual 3D Keypoints for Control »
Boyuan Chen · Pieter Abbeel · Deepak Pathak -
2021 Poster: State Entropy Maximization with Random Encoders for Efficient Exploration »
Younggyo Seo · Lili Chen · Jinwoo Shin · Honglak Lee · Pieter Abbeel · Kimin Lee -
2021 Poster: MSA Transformer »
Roshan Rao · Jason Liu · Robert Verkuil · Joshua Meier · John Canny · Pieter Abbeel · Tom Sercu · Alexander Rives -
2021 Spotlight: MSA Transformer »
Roshan Rao · Jason Liu · Robert Verkuil · Joshua Meier · John Canny · Pieter Abbeel · Tom Sercu · Alexander Rives -
2021 Spotlight: State Entropy Maximization with Random Encoders for Efficient Exploration »
Younggyo Seo · Lili Chen · Jinwoo Shin · Honglak Lee · Pieter Abbeel · Kimin Lee -
2021 Spotlight: Unsupervised Learning of Visual 3D Keypoints for Control »
Boyuan Chen · Pieter Abbeel · Deepak Pathak -
2021 : Part 2: Unsupervised Pre-Training in RL »
Pieter Abbeel -
2021 Tutorial: Unsupervised Learning for Reinforcement Learning »
Aravind Srinivas · Pieter Abbeel -
2020 Workshop: 2nd ICML Workshop on Human in the Loop Learning (HILL) »
Shanghang Zhang · Xin Wang · Fisher Yu · Jiajun Wu · Trevor Darrell -
2020 Poster: Video Prediction via Example Guidance »
Jingwei Xu · Harry (Huazhe) Xu · Bingbing Ni · Xiaokang Yang · Trevor Darrell -
2020 Poster: CURL: Contrastive Unsupervised Representations for Reinforcement Learning »
Michael Laskin · Aravind Srinivas · Pieter Abbeel -
2020 Poster: Hallucinative Topological Memory for Zero-Shot Visual Planning »
Kara Liu · Thanard Kurutach · Christine Tung · Pieter Abbeel · Aviv Tamar -
2020 Poster: Frustratingly Simple Few-Shot Object Detection »
Xin Wang · Thomas Huang · Joseph E Gonzalez · Trevor Darrell · Fisher Yu -
2020 Poster: Planning to Explore via Self-Supervised World Models »
Ramanan Sekar · Oleh Rybkin · Kostas Daniilidis · Pieter Abbeel · Danijar Hafner · Deepak Pathak -
2020 Poster: Responsive Safety in Reinforcement Learning by PID Lagrangian Methods »
Adam Stooke · Joshua Achiam · Pieter Abbeel -
2020 Poster: Variable Skipping for Autoregressive Range Density Estimation »
Eric Liang · Zongheng Yang · Ion Stoica · Pieter Abbeel · Yan Duan · Peter Chen -
2020 Poster: Hierarchically Decoupled Imitation For Morphological Transfer »
Donald Hejna · Lerrel Pinto · Pieter Abbeel -
2019 : Fisher Yu: "Motion and Prediction for Autonomous Driving" »
Fisher Yu · Trevor Darrell -
2019 : Learning to Reason: Modular and Relational Representations for Visual Questions and Referring Expressions »
Kate Saenko -
2019 Workshop: Workshop on Self-Supervised Learning »
Aaron van den Oord · Yusuf Aytar · Carl Doersch · Carl Vondrick · Alec Radford · Pierre Sermanet · Amir Zamir · Pieter Abbeel -
2019 Poster: Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent Variables »
Friso Kingma · Pieter Abbeel · Jonathan Ho -
2019 Poster: On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference »
Rohin Shah · Noah Gundotra · Pieter Abbeel · Anca Dragan -
2019 Oral: On the Feasibility of Learning, Rather than Assuming, Human Biases for Reward Inference »
Rohin Shah · Noah Gundotra · Pieter Abbeel · Anca Dragan -
2019 Oral: Bit-Swap: Recursive Bits-Back Coding for Lossless Compression with Hierarchical Latent Variables »
Friso Kingma · Pieter Abbeel · Jonathan Ho -
2019 Poster: Domain Agnostic Learning with Disentangled Representations »
Xingchao Peng · Zijun Huang · Ximeng Sun · Kate Saenko -
2019 Poster: Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules »
Daniel Ho · Eric Liang · Peter Chen · Ion Stoica · Pieter Abbeel -
2019 Poster: Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design »
Jonathan Ho · Peter Chen · Aravind Srinivas · Rocky Duan · Pieter Abbeel -
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: Flow++: Improving Flow-Based Generative Models with Variational Dequantization and Architecture Design »
Jonathan Ho · Peter Chen · Aravind Srinivas · Rocky Duan · Pieter Abbeel -
2019 Oral: Population Based Augmentation: Efficient Learning of Augmentation Policy Schedules »
Daniel Ho · Eric Liang · Peter Chen · Ion Stoica · Pieter Abbeel -
2019 Oral: Domain Agnostic Learning with Disentangled Representations »
Xingchao Peng · Zijun Huang · Ximeng Sun · Kate Saenko -
2019 Oral: SOLAR: Deep Structured Representations for Model-Based Reinforcement Learning »
Marvin Zhang · Sharad Vikram · Laura Smith · Pieter Abbeel · Matthew Johnson · Sergey Levine -
2018 Poster: CyCADA: Cycle-Consistent Adversarial Domain Adaptation »
Judy Hoffman · Eric Tzeng · Taesung Park · Jun-Yan Zhu · Philip Isola · Kate Saenko · Alexei Efros · Trevor Darrell -
2018 Oral: CyCADA: Cycle-Consistent Adversarial Domain Adaptation »
Judy Hoffman · Eric Tzeng · Taesung Park · Jun-Yan Zhu · Philip Isola · Kate Saenko · Alexei Efros · Trevor Darrell -
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: PixelSNAIL: An Improved Autoregressive Generative Model »
Xi Chen · Nikhil Mishra · Mostafa Rohaninejad · Pieter Abbeel -
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: PixelSNAIL: An Improved Autoregressive Generative Model »
Xi Chen · Nikhil Mishra · Mostafa Rohaninejad · Pieter Abbeel -
2018 Poster: Automatic Goal Generation for Reinforcement Learning Agents »
Carlos Florensa · David Held · Xinyang Geng · Pieter Abbeel -
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: Automatic Goal Generation for Reinforcement Learning Agents »
Carlos Florensa · David Held · Xinyang Geng · Pieter Abbeel -
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 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: Prediction and Control with Temporal Segment Models »
Nikhil Mishra · Pieter Abbeel · Igor Mordatch -
2017 Poster: Reinforcement Learning with Deep Energy-Based Policies »
Tuomas Haarnoja · Haoran Tang · Pieter Abbeel · Sergey Levine -
2017 Poster: Constrained Policy Optimization »
Joshua Achiam · David Held · Aviv Tamar · Pieter Abbeel -
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: Prediction and Control with Temporal Segment Models »
Nikhil Mishra · Pieter Abbeel · Igor Mordatch -
2017 Talk: Reinforcement Learning with Deep Energy-Based Policies »
Tuomas Haarnoja · Haoran Tang · Pieter Abbeel · Sergey Levine -
2017 Talk: Constrained Policy Optimization »
Joshua Achiam · David Held · Aviv Tamar · Pieter Abbeel