Timezone: »
We introduce a new approach for comparing reinforcement learning policies, using Wasserstein distances (WDs) in a newly defined latent behavioral space. We show that by utilizing the dual formulation of the WD, we can learn score functions over policy behaviors that can in turn be used to lead policy optimization towards (or away from) (un)desired behaviors. Combined with smoothed WDs, the dual formulation allows us to devise efficient algorithms that take stochastic gradient descent steps through WD regularizers. We incorporate these regularizers into two novel on-policy algorithms, Behavior-Guided Policy Gradient and Behavior-Guided Evolution Strategies, which we demonstrate can outperform existing methods in a variety of challenging environments. We also provide an open source demo.
Author Information
Aldo Pacchiano (UC Berkeley)
Jack Parker-Holder (University of Oxford)
Yunhao Tang (Columbia University)
Krzysztof Choromanski (Google)
Anna Choromanska (NYU Tandon School of Engineering)
Michael Jordan (UC Berkeley)
More from the Same Authors
-
2020 Workshop: Workshop on eXtreme Classification: Theory and Applications »
Anna Choromanska · John Langford · Maryam Majzoubi · Yashoteja Prabhu -
2020 Poster: Monte-Carlo Tree Search as Regularized Policy Optimization »
Jean-Bastien Grill · Florent Altché · Yunhao Tang · Thomas Hubert · Michal Valko · Ioannis Antonoglou · Remi Munos -
2020 Poster: On Thompson Sampling with Langevin Algorithms »
Eric Mazumdar · Aldo Pacchiano · Yian Ma · Michael Jordan · Peter Bartlett -
2020 Poster: Accelerated Message Passing for Entropy-Regularized MAP Inference »
Jonathan Lee · Aldo Pacchiano · Peter Bartlett · Michael Jordan -
2020 Poster: Stochastic Flows and Geometric Optimization on the Orthogonal Group »
Krzysztof Choromanski · David Cheikhi · Jared Quincy Davis · Valerii Likhosherstov · Achille Nazaret · Achraf Bahamou · Xingyou Song · Mrugank Akarte · Jack Parker-Holder · Jacob Bergquist · Yuan Gao · Aldo Pacchiano · Tamas Sarlos · Adrian Weller · Vikas Sindhwani -
2020 Poster: On Gradient Descent Ascent for Nonconvex-Concave Minimax Problems »
Darren Lin · Chi Jin · Michael Jordan -
2020 Poster: Continuous-time Lower Bounds for Gradient-based Algorithms »
Michael Muehlebach · Michael Jordan -
2020 Poster: Stochastic Gradient and Langevin Processes »
Xiang Cheng · Dong Yin · Peter Bartlett · Michael Jordan -
2020 Poster: Reinforcement Learning for Integer Programming: Learning to Cut »
Yunhao Tang · Shipra Agrawal · Yuri Faenza -
2020 Poster: Finite-Time Last-Iterate Convergence for Multi-Agent Learning in Games »
Darren Lin · Zhengyuan Zhou · Panayotis Mertikopoulos · Michael Jordan -
2020 Poster: Ready Policy One: World Building Through Active Learning »
Philip Ball · Jack Parker-Holder · Aldo Pacchiano · Krzysztof Choromanski · Stephen Roberts -
2020 Poster: Taylor Expansion Policy Optimization »
Yunhao Tang · Michal Valko · Remi Munos -
2020 Poster: What is Local Optimality in Nonconvex-Nonconcave Minimax Optimization? »
Chi Jin · Praneeth Netrapalli · Michael Jordan -
2019 Workshop: Workshop on AI for autonomous driving »
Anna Choromanska · Larry Jackel · Li Erran Li · Juan Carlos Niebles · Adrien Gaidon · Wei-Lun Chao · Ingmar Posner · Wei-Lun (Harry) Chao -
2019 Poster: Bridging Theory and Algorithm for Domain Adaptation »
Yuchen Zhang · Tianle Liu · Mingsheng Long · Michael Jordan -
2019 Oral: Bridging Theory and Algorithm for Domain Adaptation »
Yuchen Zhang · Tianle Liu · Mingsheng Long · Michael Jordan -
2019 Poster: Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers »
Hong Liu · Mingsheng Long · Jianmin Wang · Michael Jordan -
2019 Poster: Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation »
Kaichao You · Ximei Wang · Mingsheng Long · Michael Jordan -
2019 Poster: A Dynamical Systems Perspective on Nesterov Acceleration »
Michael Muehlebach · Michael Jordan -
2019 Poster: Theoretically Principled Trade-off between Robustness and Accuracy »
Hongyang Zhang · Yaodong Yu · Jiantao Jiao · Eric Xing · Laurent El Ghaoui · Michael Jordan -
2019 Oral: A Dynamical Systems Perspective on Nesterov Acceleration »
Michael Muehlebach · Michael Jordan -
2019 Oral: Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation »
Kaichao You · Ximei Wang · Mingsheng Long · Michael Jordan -
2019 Oral: Transferable Adversarial Training: A General Approach to Adapting Deep Classifiers »
Hong Liu · Mingsheng Long · Jianmin Wang · Michael Jordan -
2019 Oral: Theoretically Principled Trade-off between Robustness and Accuracy »
Hongyang Zhang · Yaodong Yu · Jiantao Jiao · Eric Xing · Laurent El Ghaoui · Michael Jordan -
2019 Poster: On Efficient Optimal Transport: An Analysis of Greedy and Accelerated Mirror Descent Algorithms »
Darren Lin · Nhat Ho · Michael Jordan -
2019 Poster: Online learning with kernel losses »
Niladri S Chatterji · Aldo Pacchiano · Peter Bartlett -
2019 Poster: Rao-Blackwellized Stochastic Gradients for Discrete Distributions »
Runjing Liu · Jeffrey Regier · Nilesh Tripuraneni · Michael Jordan · Jon McAuliffe -
2019 Oral: Rao-Blackwellized Stochastic Gradients for Discrete Distributions »
Runjing Liu · Jeffrey Regier · Nilesh Tripuraneni · Michael Jordan · Jon McAuliffe -
2019 Oral: Online learning with kernel losses »
Niladri S Chatterji · Aldo Pacchiano · Peter Bartlett -
2019 Oral: On Efficient Optimal Transport: An Analysis of Greedy and Accelerated Mirror Descent Algorithms »
Darren Lin · Nhat Ho · Michael Jordan -
2018 Poster: On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo »
Niladri S Chatterji · Nicolas Flammarion · Yian Ma · Peter Bartlett · Michael Jordan -
2018 Poster: RLlib: Abstractions for Distributed Reinforcement Learning »
Eric Liang · Richard Liaw · Robert Nishihara · Philipp Moritz · Roy Fox · Ken Goldberg · Joseph Gonzalez · Michael Jordan · Ion Stoica -
2018 Oral: On the Theory of Variance Reduction for Stochastic Gradient Monte Carlo »
Niladri S Chatterji · Nicolas Flammarion · Yian Ma · Peter Bartlett · Michael Jordan -
2018 Oral: RLlib: Abstractions for Distributed Reinforcement Learning »
Eric Liang · Richard Liaw · Robert Nishihara · Philipp Moritz · Roy Fox · Ken Goldberg · Joseph Gonzalez · Michael Jordan · Ion Stoica -
2018 Poster: SAFFRON: an Adaptive Algorithm for Online Control of the False Discovery Rate »
Aaditya Ramdas · Tijana Zrnic · Martin Wainwright · Michael Jordan -
2018 Oral: SAFFRON: an Adaptive Algorithm for Online Control of the False Discovery Rate »
Aaditya Ramdas · Tijana Zrnic · Martin Wainwright · Michael Jordan -
2018 Poster: Learning to Explain: An Information-Theoretic Perspective on Model Interpretation »
Jianbo Chen · Le Song · Martin Wainwright · Michael Jordan -
2018 Oral: Learning to Explain: An Information-Theoretic Perspective on Model Interpretation »
Jianbo Chen · Le Song · Martin Wainwright · Michael Jordan -
2017 Poster: How to Escape Saddle Points Efficiently »
Chi Jin · Rong Ge · Praneeth Netrapalli · Sham Kakade · Michael Jordan -
2017 Talk: How to Escape Saddle Points Efficiently »
Chi Jin · Rong Ge · Praneeth Netrapalli · Sham Kakade · Michael Jordan -
2017 Poster: Deep Transfer Learning with Joint Adaptation Networks »
Mingsheng Long · Han Zhu · Jianmin Wang · Michael Jordan -
2017 Poster: Breaking Locality Accelerates Block Gauss-Seidel »
Stephen Tu · Shivaram Venkataraman · Ashia Wilson · Alex Gittens · Michael Jordan · Benjamin Recht -
2017 Talk: Deep Transfer Learning with Joint Adaptation Networks »
Mingsheng Long · Han Zhu · Jianmin Wang · Michael Jordan -
2017 Talk: Breaking Locality Accelerates Block Gauss-Seidel »
Stephen Tu · Shivaram Venkataraman · Ashia Wilson · Alex Gittens · Michael Jordan · Benjamin Recht