Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning

9 October 2022

Jianye Hao

Papers citing "Decomposed Mutual Information Optimization for Generalized Context in Meta-Reinforcement Learning"

28 / 28 papers shown

Title
A Relational Intervention Approach for Unsupervised Dynamics Generalization in Model-Based Reinforcement Learning Jinpei Guo Biwei Huang Dacheng Tao 59 20 0 09 Jun 2022
PAnDR: Fast Adaptation to New Environments from Offline Experiences via Decoupling Policy and Environment Representations Tong Sang Hongyao Tang Yi-An Ma Jianye Hao Yan Zheng Zhaopeng Meng Boyan Li Zhen Wang OffRL 63 5 0 06 Apr 2022
Replay-Guided Adversarial Environment Design Minqi Jiang Michael Dennis Jack Parker-Holder Jakob N. Foerster Edward Grefenstette Tim Rocktaschel 203 102 0 06 Oct 2021
Decomposed Mutual Information Estimation for Contrastive Representation Learning Alessandro Sordoni Nouha Dziri Hannes Schulz Geoffrey J. Gordon Philip Bachman Rémi Tachet des Combes SSL 67 30 0 25 Jun 2021
Improving Context-Based Meta-Reinforcement Learning with Self-Supervised Trajectory Contrastive Learning Bernie Wang Si-ting Xu Kurt Keutzer Yang Gao Bichen Wu SSL OffRL 47 7 0 10 Mar 2021
Provably Improved Context-Based Offline Meta-RL with Attention and Contrastive Learning Lanqing Li Yuanhao Huang Mingzhe Chen Siteng Luo Dijun Luo Junzhou Huang OffRL 30 3 0 22 Feb 2021
Decoupling Value and Policy for Generalization in Reinforcement Learning Roberta Raileanu Rob Fergus DRL OffRL 71 99 0 20 Feb 2021
Emergent Complexity and Zero-shot Transfer via Unsupervised Environment Design Michael Dennis Natasha Jaques Eugene Vinitsky Alexandre M. Bayen Stuart J. Russell Andrew Critch Sergey Levine 90 237 0 03 Dec 2020
Prioritized Level Replay Minqi Jiang Edward Grefenstette Tim Rocktaschel OffRL 81 160 0 08 Oct 2020
Unsupervised Learning of Visual Features by Contrasting Cluster Assignments Mathilde Caron Ishan Misra Julien Mairal Priya Goyal Piotr Bojanowski Armand Joulin OCL SSL 267 4,101 0 17 Jun 2020
Bootstrap your own latent: A new approach to self-supervised Learning Jean-Bastien Grill Florian Strub Florent Altché Corentin Tallec Pierre Harvey Richemond ... M. G. Azar Bilal Piot Koray Kavukcuoglu Rémi Munos Michal Valko SSL 401 6,844 0 13 Jun 2020
Deep Reinforcement and InfoMax Learning Bogdan Mazoure Rémi Tachet des Combes T. Doan Philip Bachman R. Devon Hjelm AI4CE 65 109 0 12 Jun 2020
Context-aware Dynamics Model for Generalization in Model-Based Reinforcement Learning Kimin Lee Younggyo Seo Seunghyun Lee Honglak Lee Jinwoo Shin 97 133 0 14 May 2020
Leveraging Procedural Generation to Benchmark Reinforcement Learning K. Cobbe Christopher Hesse Jacob Hilton John Schulman 87 557 0 03 Dec 2019
VariBAD: A Very Good Method for Bayes-Adaptive Deep RL via Meta-Learning L. Zintgraf K. Shiarlis Maximilian Igl Sebastian Schulze Y. Gal Katja Hofmann Shimon Whiteson OffRL 65 279 0 18 Oct 2019
Understanding the Limitations of Variational Mutual Information Estimators Jiaming Song Stefano Ermon SSL DRL 74 204 0 14 Oct 2019
Formal Limitations on the Measurement of Mutual Information David A. McAllester K. Stratos SSL 72 277 0 10 Nov 2018
Assessing Generalization in Deep Reinforcement Learning Charles Packer Katelyn Gao Jernej Kos Philipp Krahenbuhl V. Koltun Basel Alomair OffRL 122 238 0 29 Oct 2018
ProMP: Proximal Meta-Policy Search Jonas Rothfuss Dennis Lee I. Clavera Tamim Asfour Pieter Abbeel 67 211 0 16 Oct 2018
Learning deep representations by mutual information estimation and maximization R. Devon Hjelm A. Fedorov Samuel Lavoie-Marchildon Karan Grewal Phil Bachman Adam Trischler Yoshua Bengio SSL DRL 352 2,672 0 20 Aug 2018
Learning to Adapt in Dynamic, Real-World Environments Through Meta-Reinforcement Learning Anusha Nagabandi I. Clavera Simin Liu R. Fearing Pieter Abbeel Sergey Levine Chelsea Finn 130 553 0 30 Mar 2018
Meta-Reinforcement Learning of Structured Exploration Strategies Abhishek Gupta Russell Mendonca YuXuan Liu Pieter Abbeel Sergey Levine OffRL 113 349 0 20 Feb 2018
Deep Reinforcement Learning that Matters Peter Henderson Riashat Islam Philip Bachman Joelle Pineau Doina Precup David Meger OffRL 132 1,963 0 19 Sep 2017
Reinterpreting Importance-Weighted Autoencoders Chris Cremer Q. Morris David Duvenaud BDL FAtt 120 94 0 10 Apr 2017
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks Chelsea Finn Pieter Abbeel Sergey Levine OOD 833 11,952 0 09 Mar 2017
Preparing for the Unknown: Learning a Universal Policy with Online System Identification Wenhao Yu Jie Tan Chenxi Liu Greg Turk OffRL 101 309 0 08 Feb 2017
High-Dimensional Continuous Control Using Generalized Advantage Estimation John Schulman Philipp Moritz Sergey Levine Michael I. Jordan Pieter Abbeel OffRL 133 3,439 0 08 Jun 2015
Efficient Estimation of Word Representations in Vector Space Tomas Mikolov Kai Chen G. Corrado J. Dean 3DV 693 31,553 0 16 Jan 2013