Timezone: »
Poster
Redeeming intrinsic rewards via constrained optimization
Eric Chen · Zhang-Wei Hong · Joni Pajarinen · Pulkit Agrawal
State-of-the-art reinforcement learning (RL) algorithms typically use random sampling (e.g., $\epsilon$-greedy) for exploration, but this method fails on hard exploration tasks like Montezuma's Revenge. To address the challenge of exploration, prior works incentivize exploration by rewarding the agent when it visits novel states. Such intrinsic rewards (also called exploration bonus or curiosity) often lead to excellent performance on hard exploration tasks. However, on easy exploration tasks, the agent gets distracted by intrinsic rewards and performs unnecessary exploration even when sufficient task (also called extrinsic) reward is available. Consequently, such an overly curious agent performs worse than an agent trained with only task reward. Such inconsistency in performance across tasks prevents the widespread use of intrinsic rewards with RL algorithms. We propose a principled constrained optimization procedure called Extrinsic-Intrinsic Policy Optimization (EIPO) that automatically tunes the importance of the intrinsic reward: it suppresses the intrinsic reward when exploration is unnecessary and increases it when exploration is required. The results is superior exploration that does not require manual tuning in balancing the intrinsic reward against the task reward. Consistent performance gains across sixty-one ATARI games validate our claim. The code is available at https://github.com/Improbable-AI/eipo.
Author Information
Eric Chen (Massachusetts Institute of Technology)
Zhang-Wei Hong (MIT)
Joni Pajarinen (Aalto University)
Pulkit Agrawal (MIT)
More from the Same Authors
-
2021 : 3D Neural Scene Representations for Visuomotor Control »
Yunzhu Li · Shuang Li · Vincent Sitzmann · Pulkit Agrawal · Antonio Torralba -
2021 : 3D Neural Scene Representations for Visuomotor Control »
Yunzhu Li · Shuang Li · Vincent Sitzmann · Pulkit Agrawal · Antonio Torralba -
2021 : Adaptive Behavior Cloning Regularization for Stable Offline-to-Online Reinforcement Learning »
Yi Zhao · Rinu Boney · Alexander Ilin · Juho Kannala · Joni Pajarinen -
2022 : Is Conditional Generative Modeling all you need for Decision-Making? »
Anurag Ajay · Yilun Du · Abhi Gupta · Josh Tenenbaum · Tommi Jaakkola · Pulkit Agrawal -
2022 : Learning to Extrapolate: A Transductive Approach »
Aviv Netanyahu · Abhishek Gupta · Max Simchowitz · Kaiqing Zhang · Pulkit Agrawal -
2022 : Constrained Imitation Q-learning with Earth Mover’s Distance reward »
WENYAN Yang · Nataliya Strokina · Joni Pajarinen · Joni-kristian Kamarainen -
2022 : Fast Adaptation via Human Diagnosis of Task Distribution Shift »
Andi Peng · Mark Ho · Aviv Netanyahu · Julie A Shah · Pulkit Agrawal -
2022 : Aligning Robot Representations with Humans »
Andreea Bobu · Andi Peng · Pulkit Agrawal · Julie A Shah · Anca Dragan -
2023 Poster: Self-Supervised Reinforcement Learning that Transfers using Random Features »
Boyuan Chen · Chuning Zhu · Pulkit Agrawal · Kaiqing Zhang · Abhishek Gupta -
2023 Poster: Breadcrumbs to the Goal: Supervised Goal Selection from Human-in-the-Loop Feedback »
Marcel Torne Villasevil · Max Balsells I Pamies · Zihan Wang · Samedh Desai · Tao Chen · Pulkit Agrawal · Abhishek Gupta -
2023 Poster: Human-Guided Complexity-Controlled Abstractions »
Andi Peng · Mycal Tucker · Eoin Kenny · Noga Zaslavsky · Pulkit Agrawal · Julie A Shah -
2023 Poster: Hierarchical Planning with Foundation Models »
Anurag Ajay · Seungwook Han · Yilun Du · Shuang Li · Abhi Gupta · Tommi Jaakkola · Josh Tenenbaum · Leslie Kaelbling · Akash Srivastava · Pulkit Agrawal -
2023 Poster: Hybrid Search for Efficient Planning with Completeness Guarantees »
Kalle Kujanpää · Joni Pajarinen · Alexander Ilin -
2023 Poster: Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets »
Zhang-Wei Hong · Aviral Kumar · Sathwik Karnik · Abhishek Bhandwaldar · Akash Srivastava · Joni Pajarinen · Romain Laroche · Abhishek Gupta · Pulkit Agrawal -
2022 : Visual Pre-training for Navigation: What Can We Learn from Noise? »
Felix Yanwei Wang · Ching-Yun Ko · Pulkit Agrawal -
2022 Poster: Distributionally Adaptive Meta Reinforcement Learning »
Anurag Ajay · Abhishek Gupta · Dibya Ghosh · Sergey Levine · Pulkit Agrawal -
2021 : 3D Neural Scene Representations for Visuomotor Control »
Yunzhu Li · Shuang Li · Vincent Sitzmann · Pulkit Agrawal · Antonio Torralba -
2021 Workshop: 2nd Workshop on Self-Supervised Learning: Theory and Practice »
Pengtao Xie · Ishan Misra · Pulkit Agrawal · Abdelrahman Mohamed · Shentong Mo · Youwei Liang · Jeannette Bohg · Kristina N Toutanova -
2020 Workshop: Self-Supervised Learning -- Theory and Practice »
Pengtao Xie · Shanghang Zhang · Pulkit Agrawal · Ishan Misra · Cynthia Rudin · Abdelrahman Mohamed · Wenzhen Yuan · Barret Zoph · Laurens van der Maaten · Xingyi Yang · Eric Xing -
2020 Session: Orals & Spotlights Track 09: Reinforcement Learning »
Pulkit Agrawal · Mohammad Ghavamzadeh -
2019 : Poster Session »
Matthia Sabatelli · Adam Stooke · Amir Abdi · Paulo Rauber · Leonard Adolphs · Ian Osband · Hardik Meisheri · Karol Kurach · Johannes Ackermann · Matt Benatan · GUO ZHANG · Chen Tessler · Dinghan Shen · Mikayel Samvelyan · Riashat Islam · Murtaza Dalal · Luke Harries · Andrey Kurenkov · Konrad Żołna · Sudeep Dasari · Kristian Hartikainen · Ofir Nachum · Kimin Lee · Markus Holzleitner · Vu Nguyen · Francis Song · Christopher Grimm · Felipe Leno da Silva · Yuping Luo · Yifan Wu · Alex Lee · Thomas Paine · Wei-Yang Qu · Daniel Graves · Yannis Flet-Berliac · Yunhao Tang · Suraj Nair · Matthew Hausknecht · Akhil Bagaria · Simon Schmitt · Bowen Baker · Paavo Parmas · Benjamin Eysenbach · Lisa Lee · Siyu Lin · Daniel Seita · Abhishek Gupta · Riley Simmons-Edler · Yijie Guo · Kevin Corder · Vikash Kumar · Scott Fujimoto · Adam Lerer · Ignasi Clavera Gilaberte · Nicholas Rhinehart · Ashvin Nair · Ge Yang · Lingxiao Wang · Sungryull Sohn · J. Fernando Hernandez-Garcia · Xian Yeow Lee · Rupesh Srivastava · Khimya Khetarpal · Chenjun Xiao · Luckeciano Carvalho Melo · Rishabh Agarwal · Tianhe Yu · Glen Berseth · Devendra Singh Chaplot · Jie Tang · Anirudh Srinivasan · Tharun Kumar Reddy Medini · Aaron Havens · Misha Laskin · Asier Mujika · Rohan Saphal · Joseph Marino · Alex Ray · Joshua Achiam · Ajay Mandlekar · Zhuang Liu · Danijar Hafner · Zhiwen Tang · Ted Xiao · Michael Walton · Jeff Druce · Ferran Alet · Zhang-Wei Hong · Stephanie Chan · Anusha Nagabandi · Hao Liu · Hao Sun · Ge Liu · Dinesh Jayaraman · John Co-Reyes · Sophia Sanborn -
2019 Poster: Superposition of many models into one »
Brian Cheung · Alexander Terekhov · Yubei Chen · Pulkit Agrawal · Bruno Olshausen -
2018 Poster: Diversity-Driven Exploration Strategy for Deep Reinforcement Learning »
Zhang-Wei Hong · Tzu-Yun Shann · Shih-Yang Su · Yi-Hsiang Chang · Tsu-Jui Fu · Chun-Yi Lee -
2016 : What makes ImageNet good for Transfer Learning? »
Jacob MY Huh · Pulkit Agrawal · Alexei Efros -
2016 : Jitendra Malik and Pulkit Agrawal »
Jitendra Malik · Pulkit Agrawal -
2016 Poster: Learning to Poke by Poking: Experiential Learning of Intuitive Physics »
Pulkit Agrawal · Ashvin Nair · Pieter Abbeel · Jitendra Malik · Sergey Levine -
2016 Oral: Learning to Poke by Poking: Experiential Learning of Intuitive Physics »
Pulkit Agrawal · Ashvin Nair · Pieter Abbeel · Jitendra Malik · Sergey Levine