Timezone: »
Designing rewards for Reinforcement Learning (RL) is challenging because it needs to convey the desired task, be efficient to optimize, and be easy to compute. The latter is particularly problematic when applying RL to robotics, where detecting whether the desired configuration is reached might require considerable supervision and instrumentation. Furthermore, we are often interested in being able to reach a wide range of configurations, hence setting up a different reward every time might be unpractical. Methods like Hindsight Experience Replay (HER) have recently shown promise to learn policies able to reach many goals, without the need of a reward. Unfortunately, without tricks like resetting to points along the trajectory, HER might require many samples to discover how to reach certain areas of the state-space. In this work we propose a novel algorithm goalGAIL, which incorporates demonstrations to drastically speed up the convergence to a policy able to reach any goal, surpassing the performance of an agent trained with other Imitation Learning algorithms. Furthermore, we show our method can also be used when the available expert trajectories do not contain the actions or when the expert is suboptimal, which makes it applicable when only kinesthetic, third person or noisy demonstration is available.
Author Information
Yiming Ding (University of California, Berkeley)
Carlos Florensa (UC Berkeley)
Pieter Abbeel (UC Berkeley & covariant.ai)
Pieter Abbeel is Professor and Director of the Robot Learning Lab at UC Berkeley [2008- ], Co-Director of the Berkeley AI Research (BAIR) Lab, Co-Founder of covariant.ai [2017- ], Co-Founder of Gradescope [2014- ], Advisor to OpenAI, Founding Faculty Partner AI@TheHouse venture fund, Advisor to many AI/Robotics start-ups. He works in machine learning and robotics. In particular his research focuses on making robots learn from people (apprenticeship learning), how to make robots learn through their own trial and error (reinforcement learning), and how to speed up skill acquisition through learning-to-learn (meta-learning). His robots have learned advanced helicopter aerobatics, knot-tying, basic assembly, organizing laundry, locomotion, and vision-based robotic manipulation. He has won numerous awards, including best paper awards at ICML, NIPS and ICRA, early career awards from NSF, Darpa, ONR, AFOSR, Sloan, TR35, IEEE, and the Presidential Early Career Award for Scientists and Engineers (PECASE). Pieter's work is frequently featured in the popular press, including New York Times, BBC, Bloomberg, Wall Street Journal, Wired, Forbes, Tech Review, NPR.
Mariano Phielipp (Intel AI Labs)
Dr. Mariano Phielipp works at the Intel AI Lab inside the Intel Artificial Intelligence Products Group. His work includes research and development in deep learning, deep reinforcement learning, machine learning, and artificial intelligence. Since joining Intel, Dr. Phielipp has developed and worked on Computer Vision, Face Recognition, Face Detection, Object Categorization, Recommendation Systems, Online Learning, Automatic Rule Learning, Natural Language Processing, Knowledge Representation, Energy Based Algorithms, and other Machine Learning and AI-related efforts. Dr. Phielipp has also contributed to different disclosure committees, won an Intel division award related to Robotics, and has a large number of patents and pending patents. He has published on NeuriPS, ICML, ICLR, AAAI, IROS, IEEE, SPIE, IASTED, and EUROGRAPHICS-IEEE Conferences and Workshops.
More from the Same Authors
-
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 Poster: Denoising Diffusion Probabilistic Models »
Jonathan Ho · Ajay Jain · Pieter Abbeel -
2020 Poster: Automatic Curriculum Learning through Value Disagreement »
Yunzhi Zhang · Pieter Abbeel · Lerrel Pinto -
2020 Poster: AvE: Assistance via Empowerment »
Yuqing Du · Stas Tiomkin · Emre Kiciman · Daniel Polani · Pieter Abbeel · Anca Dragan -
2020 Poster: Reinforcement Learning with Augmented Data »
Misha Laskin · Kimin Lee · Adam Stooke · Lerrel Pinto · Pieter Abbeel · Aravind Srinivas -
2020 Poster: Generalized Hindsight for Reinforcement Learning »
Alexander Li · Lerrel Pinto · Pieter Abbeel -
2020 Poster: Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning »
Younggyo Seo · Kimin Lee · Ignasi Clavera Gilaberte · Thanard Kurutach · Jinwoo Shin · Pieter Abbeel -
2020 Poster: Language-Conditioned Imitation Learning for Robot Manipulation Tasks »
Simon Stepputtis · Joseph Campbell · Mariano Phielipp · Stefan Lee · Chitta Baral · Heni Ben Amor -
2020 Spotlight: Language-Conditioned Imitation Learning for Robot Manipulation Tasks »
Simon Stepputtis · Joseph Campbell · Mariano Phielipp · Stefan Lee · Chitta Baral · Heni Ben Amor -
2020 Spotlight: Reinforcement Learning with Augmented Data »
Misha Laskin · Kimin Lee · Adam Stooke · Lerrel Pinto · Pieter Abbeel · Aravind Srinivas -
2020 Poster: Sparse Graphical Memory for Robust Planning »
Scott Emmons · Ajay Jain · Misha Laskin · Thanard Kurutach · Pieter Abbeel · Deepak Pathak -
2020 Poster: Instance-based Generalization in Reinforcement Learning »
Martin Bertran · Natalia Martinez · Mariano Phielipp · Guillermo Sapiro -
2020 Poster: Stochastic Latent Actor-Critic: Deep Reinforcement Learning with a Latent Variable Model »
Alex X. Lee · Anusha Nagabandi · Pieter Abbeel · Sergey Levine -
2019 Workshop: Deep Reinforcement Learning »
Pieter Abbeel · Chelsea Finn · Joelle Pineau · David Silver · Satinder Singh · Joshua Achiam · Carlos Florensa · Christopher Grimm · Haoran Tang · Vivek Veeriah -
2019 Poster: Evaluating Protein Transfer Learning with TAPE »
Roshan Rao · Nicholas Bhattacharya · Neil Thomas · Yan Duan · Peter Chen · John Canny · Pieter Abbeel · Yun Song -
2019 Spotlight: Evaluating Protein Transfer Learning with TAPE »
Roshan Rao · Nicholas Bhattacharya · Neil Thomas · Yan Duan · Peter Chen · John Canny · Pieter Abbeel · Yun Song -
2019 Poster: Geometry-Aware Neural Rendering »
Joshua Tobin · Wojciech Zaremba · Pieter Abbeel -
2019 Poster: MCP: Learning Composable Hierarchical Control with Multiplicative Compositional Policies »
Xue Bin Peng · Michael Chang · Grace Zhang · Pieter Abbeel · Sergey Levine -
2019 Oral: Geometry-Aware Neural Rendering »
Joshua Tobin · Wojciech Zaremba · Pieter Abbeel -
2019 Poster: Compositional Plan Vectors »
Coline Devin · Daniel Geng · Pieter Abbeel · Trevor Darrell · Sergey Levine -
2019 Poster: On the Utility of Learning about Humans for Human-AI Coordination »
Micah Carroll · Rohin Shah · Mark Ho · Tom Griffiths · Sanjit Seshia · Pieter Abbeel · Anca Dragan -
2019 Poster: Compression with Flows via Local Bits-Back Coding »
Jonathan Ho · Evan Lohn · Pieter Abbeel -
2019 Poster: Guided Meta-Policy Search »
Russell Mendonca · Abhishek Gupta · Rosen Kralev · Pieter Abbeel · Sergey Levine · Chelsea Finn -
2019 Spotlight: Compression with Flows via Local Bits-Back Coding »
Jonathan Ho · Evan Lohn · Pieter Abbeel -
2019 Spotlight: Guided Meta-Policy Search »
Russell Mendonca · Abhishek Gupta · Rosen Kralev · Pieter Abbeel · Sergey Levine · Chelsea Finn -
2018 Workshop: Deep Reinforcement Learning »
Pieter Abbeel · David Silver · Satinder Singh · Joelle Pineau · Joshua Achiam · Rein Houthooft · Aravind Srinivas -
2018 Poster: Meta-Reinforcement Learning of Structured Exploration Strategies »
Abhishek Gupta · Russell Mendonca · YuXuan Liu · Pieter Abbeel · Sergey Levine -
2018 Poster: Learning Plannable Representations with Causal InfoGAN »
Thanard Kurutach · Aviv Tamar · Ge Yang · Stuart Russell · Pieter Abbeel -
2018 Spotlight: Meta-Reinforcement Learning of Structured Exploration Strategies »
Abhishek Gupta · Russell Mendonca · YuXuan Liu · Pieter Abbeel · Sergey Levine -
2018 Poster: Evolved Policy Gradients »
Rein Houthooft · Yuhua Chen · Phillip Isola · Bradly Stadie · Filip Wolski · OpenAI Jonathan Ho · Pieter Abbeel -
2018 Spotlight: Evolved Policy Gradients »
Rein Houthooft · Yuhua Chen · Phillip Isola · Bradly Stadie · Filip Wolski · OpenAI Jonathan Ho · Pieter Abbeel -
2018 Poster: The Importance of Sampling inMeta-Reinforcement Learning »
Bradly Stadie · Ge Yang · Rein Houthooft · Peter Chen · Yan Duan · Yuhuai Wu · Pieter Abbeel · Ilya Sutskever -
2017 Workshop: Hierarchical Reinforcement Learning »
Andrew G Barto · Doina Precup · Shie Mannor · Tom Schaul · Roy Fox · Carlos Florensa -
2017 Symposium: Deep Reinforcement Learning »
Pieter Abbeel · Yan Duan · David Silver · Satinder Singh · Junhyuk Oh · Rein Houthooft -
2017 Poster: #Exploration: A Study of Count-Based Exploration for Deep Reinforcement Learning »
Haoran Tang · Rein Houthooft · Davis Foote · Adam Stooke · OpenAI Xi Chen · Yan Duan · John Schulman · Filip DeTurck · Pieter Abbeel -
2017 Poster: Inverse Reward Design »
Dylan Hadfield-Menell · Smitha Milli · Pieter Abbeel · Stuart J Russell · Anca Dragan -
2017 Oral: Inverse Reward Design »
Dylan Hadfield-Menell · Smitha Milli · Pieter Abbeel · Stuart J Russell · Anca Dragan -
2017 Invited Talk: Deep Learning for Robotics »
Pieter Abbeel -
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: One-Shot Imitation Learning »
Yan Duan · Marcin Andrychowicz · Bradly Stadie · OpenAI Jonathan Ho · Jonas Schneider · Ilya Sutskever · Pieter Abbeel · Wojciech Zaremba -
2016 Workshop: Deep Reinforcement Learning »
David Silver · Satinder Singh · Pieter Abbeel · Peter Chen -
2016 Poster: Backprop KF: Learning Discriminative Deterministic State Estimators »
Tuomas Haarnoja · Anurag Ajay · Sergey Levine · Pieter Abbeel -
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 -
2016 Poster: Combinatorial Energy Learning for Image Segmentation »
Jeremy Maitin-Shepard · Viren Jain · Michal Januszewski · Peter Li · Pieter Abbeel -
2016 Poster: InfoGAN: Interpretable Representation Learning by Information Maximizing Generative Adversarial Nets »
Xi Chen · Peter Chen · Yan Duan · Rein Houthooft · John Schulman · Ilya Sutskever · Pieter Abbeel -
2016 Poster: VIME: Variational Information Maximizing Exploration »
Rein Houthooft · Xi Chen · Peter Chen · Yan Duan · John Schulman · Filip De Turck · Pieter Abbeel -
2016 Poster: Value Iteration Networks »
Aviv Tamar · Sergey Levine · Pieter Abbeel · YI WU · Garrett Thomas -
2016 Oral: Value Iteration Networks »
Aviv Tamar · Sergey Levine · Pieter Abbeel · YI WU · Garrett Thomas -
2016 Poster: Cooperative Inverse Reinforcement Learning »
Dylan Hadfield-Menell · Stuart J Russell · Pieter Abbeel · Anca Dragan -
2016 Tutorial: Deep Reinforcement Learning Through Policy Optimization »
Pieter Abbeel · John Schulman -
2015 Workshop: Deep Reinforcement Learning »
Pieter Abbeel · John Schulman · Satinder Singh · David Silver -
2015 Poster: Gradient Estimation Using Stochastic Computation Graphs »
John Schulman · Nicolas Heess · Theophane Weber · Pieter Abbeel -
2014 Workshop: Novel Trends and Applications in Reinforcement Learning »
Csaba Szepesvari · Marc Deisenroth · Sergey Levine · Pedro Ortega · Brian Ziebart · Emma Brunskill · Naftali Tishby · Gerhard Neumann · Daniel Lee · Sridhar Mahadevan · Pieter Abbeel · David Silver · Vicenç Gómez -
2014 Poster: Learning Neural Network Policies with Guided Policy Search under Unknown Dynamics »
Sergey Levine · Pieter Abbeel -
2014 Spotlight: Learning Neural Network Policies with Guided Policy Search under Unknown Dynamics »
Sergey Levine · Pieter Abbeel -
2012 Poster: Near Optimal Chernoff Bounds for Markov Decision Processes »
Teodor Mihai Moldovan · Pieter Abbeel -
2012 Spotlight: Near Optimal Chernoff Bounds for Markov Decision Processes »
Teodor Mihai Moldovan · Pieter Abbeel -
2010 Spotlight: On a Connection between Importance Sampling and the Likelihood Ratio Policy Gradient »
Jie Tang · Pieter Abbeel -
2010 Poster: On a Connection between Importance Sampling and the Likelihood Ratio Policy Gradient »
Jie Tang · Pieter Abbeel -
2007 Spotlight: Hierarchical Apprenticeship Learning with Application to Quadruped Locomotion »
J. Zico Kolter · Pieter Abbeel · Andrew Y Ng -
2007 Poster: Hierarchical Apprenticeship Learning with Application to Quadruped Locomotion »
J. Zico Kolter · Pieter Abbeel · Andrew Y Ng -
2006 Poster: Max-margin classification of incomplete data »
Gal Chechik · Geremy Heitz · Gal Elidan · Pieter Abbeel · Daphne Koller -
2006 Spotlight: Max-margin classification of incomplete data »
Gal Chechik · Geremy Heitz · Gal Elidan · Pieter Abbeel · Daphne Koller -
2006 Poster: An Application of Reinforcement Learning to Aerobatic Helicopter Flight »
Pieter Abbeel · Adam P Coates · Andrew Y Ng · Morgan Quigley -
2006 Talk: An Application of Reinforcement Learning to Aerobatic Helicopter Flight »
Pieter Abbeel · Adam P Coates · Andrew Y Ng · Morgan Quigley