DeepMDP: Learning Continuous Latent Space Models for Representation Learning

Carles Gelada, Saurabh Kumar, Jacob Buckman, Ofir Nachum, Marc G. Bellemare

Type: Preprint

Publication Date: 2019-06-06

Citations: 47

Locations

arXiv (Cornell University) - View

Similar Works

Action	Title	Year	Authors
+	DeepMDP: Learning Continuous Latent Space Models for Representation Learning	2019	Carles Gelada Saurabh Kumar Jacob Buckman Ofir Nachum Marc G. Bellemare
+	Harnessing Discrete Representations For Continual Reinforcement Learning	2023	Edan Meyer Adam White Marlos C. Machado
+ PDF Chat	Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning	2024	Marvin Alles Philip Becker-Ehmck Patrick van der Smagt Maximilian Karl
+	Learning Temporally-Consistent Representations for Data-Efficient Reinforcement Learning	2021	Trevor McInroe Lukas Schäfer Stefano V. Albrecht
+	Low-Dimensional State and Action Representation Learning with MDP Homomorphism Metrics	2021	Nicolò Botteghi Mannes Poel Beril Sırmaçek Christoph Brüne
+	Learning World Models with Identifiable Factorization	2023	Yu-Ren Liu Biwei Huang Zhengmao Zhu Honglong Tian Mingming Gong Yang Yu Kun Zhang
+	Bootstrap Latent-Predictive Representations for Multitask Reinforcement Learning	2020	Daniel Guo Bernardo Ávila Pires Bilal Piot Jean-Bastien Grill Florent Altché Rémi Munos Mohammad Gheshlaghi Azar
+	Understanding and Addressing the Pitfalls of Bisimulation-based Representations in Offline Reinforcement Learning	2023	Hongyu Zang Xin Li Leiji Zhang Liu Yang Baigui Sun Riashat Islam Rémi Tachet des Combes Romain Laroche
+	Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning Approach	2022	Xuezhou Zhang Yuda Song Masatoshi Uehara Mengdi Wang Alekh Agarwal Wen Sun
+ PDF Chat	Rich-Observation Reinforcement Learning with Continuous Latent Dynamics	2024	Yuda Song Lili Wu Dylan J. Foster Akshay Krishnamurthy
+	Representation Learning in Deep RL via Discrete Information Bottleneck	2022	Riashat Islam Hongyu Zang Manan Tomar Aniket Didolkar Md Mofijul Islam Samin Yeasar Arnob Iqbal Tariq Xin Li Anirudh Goyal Nicolas Heess
+	Learning Invariant Representations for Reinforcement Learning without Reconstruction	2020	Amy Zhang Rowan McAllister Roberto Calandra Yarin Gal Sergey Levine
+	Learning Invariant Representations for Reinforcement Learning without Reconstruction	2020	Amy Zhang Rowan McAllister Roberto Calandra Yarin Gal Sergey Levine
+ PDF Chat	Representation Learning For Efficient Deep Multi-Agent Reinforcement Learning	2024	Dom Huh Prasant Mohapatra
+	Learning Markov State Abstractions for Deep Reinforcement Learning	2021	Cameron Allen Neev Parikh Omer Gottesman George Konidaris
+	Deep Model-Based Reinforcement Learning for High-Dimensional Problems, a Survey	2020	Aske Plaat Walter A. Kosters Mike Preuß
+	Deep Model-Based Reinforcement Learning for High-Dimensional Problems, a Survey	2020	Aske Plaat Walter A. Kosters Mike Preuß
+	Latent Variable Representation for Reinforcement Learning	2022	Tongzheng Ren Chenjun Xiao Tianjun Zhang Na Li Zhaoran Wang Sujay Sanghavi Dale Schuurmans Bo Dai
+	Learning Latent State Spaces for Planning through Reward Prediction	2019	Aaron Havens Yi Ouyang Prabhat Nagarajan Yasuhiro Fujita
+	Model-Based Deep Reinforcement Learning for High-Dimensional Problems, a Survey.	2020	Aske Plaat Walter A. Kosters Mike Preuß

Works That Cite This (39)

Action	Title	Year	Authors
+ PDF Chat	Mastering Atari, Go, chess and shogi by planning with a learned model	2020	Julian Schrittwieser Ioannis Antonoglou Thomas Hubert Karen Simonyan Laurent Sifre Simon Schmitt Arthur Guez Edward Lockhart Demis Hassabis Thore Graepel
+	Learning Robust State Abstractions for Hidden-Parameter Block MDPs	2020	Amy Zhang Shagun Sodhani Khimya Khetarpal Joëlle Pineau
+	Return-Based Contrastive Representation Learning for Reinforcement Learning	2021	Guoqing Liu Chuheng Zhang Li Zhao Tao Qin Jinhua Zhu Li Jian Nenghai Yu Tie‐Yan Liu
+	Contrastive Learning of Structured World Models	2019	Thomas Kipf Elise van der Pol Max Welling
+	Which Mutual-Information Representation Learning Objectives are Sufficient for Control?	2021	Kate Rakelly Abhishek Gupta Carlos Florensa Sergey Levine
+	Multi-Task Reinforcement Learning as a Hidden-Parameter Block MDP	2020	Amy Zhang Shagun Sodhani Khimya Khetarpal Joëlle Pineau
+	Learning Representations for Pixel-based Control: What Matters and Why?	2021	Manan Tomar Utkarsh Mishra Amy Zhang Matthew E. Taylor
+	Deep Reinforcement Learning and Its Neuroscientific Implications	2020	Matthew Botvinick Jane X. Wang Will Dabney Kevin J Miller Zeb Kurth‐Nelson
+	A Geometric Perspective on Optimal Representations for Reinforcement Learning	2019	Marc G. Bellemare Will Dabney Robert Dadashi Adrien Ali Taïga Pablo Samuel Castro Nicolas Le Roux Dale Schuurmans Tor Lattimore Clare Lyle
+	Towards Robust Bisimulation Metric Learning	2021	Mete Kemertas Tristan Aumentado-Armstrong

Works Cited by This (33)

Action	Title	Year	Authors
+	Equivalence of distance-based and RKHS-based statistics in hypothesis testing	2013	Dino Sejdinović Bharath K. Sriperumbudur Arthur Gretton Kenji Fukumizu
+	Convex Analysis and Nonlinear Optimization	2006	Jonathan M. Borwein Adrian S. Lewis
+	A kernel two-sample test	2012	Arthur Gretton Karsten Borgwardt Malte J. Rasch Bernhard Schölkopf Alexander J. Smola
+	Integral Probability Metrics and Their Generating Classes of Functions	1997	Alfred Müller
+	The Cramer Distance as a Solution to Biased Wasserstein Gradients	2017	Marc G. Bellemare Ivo Danihelka Will Dabney Shakir Mohamed Balaji Lakshminarayanan Stephan Hoyer Rémi Munos
+	Visual Interaction Networks	2017	Nicholas Watters Andrea Tacchetti Théophane Weber Razvan Pascanu Peter Battaglia Daniel Zoran
+	Probabilistic Recurrent State-Space Models	2018	Andreas Doerr Christian Daniel Martin Schiegg Duy Nguyen-Tuong Stefan Schaal Marc Toussaint Sebastian Trimpe
+	Learning and Querying Fast Generative Models for Reinforcement Learning	2018	Lars Buesing Théophane Weber Sébastien Racanière S. M. Ali Eslami Danilo Jimenez Rezende David Reichert Fabio Viola Frederic Besse Karol Gregor Demis Hassabis
+	Model-Based Value Estimation for Efficient Model-Free Reinforcement Learning	2018	Vladimir Feinberg Alvin Wan Ion Stoica Michael I. Jordan Joseph E. Gonzalez Sergey Levine
+	Regularisation of Neural Networks by Enforcing Lipschitz Continuity	2018	Henry Gouk Eibe Frank Bernhard Pfahringer Michael J. Cree