About

In recent years, the use of deep neural networks as function approximators has enabled researchers to extend reinforcement learning techniques to solve increasingly complex control tasks. The emerging field of deep reinforcement learning has led to remarkable empirical results in rich and varied domains like robotics, strategy games, and multi-agent interactions. This workshop will bring together researchers working at the intersection of deep learning and reinforcement learning, and it will help interested researchers outside of the field gain a high-level view about the current state of the art and potential directions for future contributions.

For previous editions, please visit NeurIPS 2021, 2020, 2019, 2018, 2017, 2016, 2015.

Attending the Workshop

We will post the live-stream link here. Once it's available, chats to ask questions, GatherTown links for poster sessions, and all pre-recorded videos can be viewed through that link. NeurIPS workshop registration is required.

Important Dates and Deadlines

• Paper submission deadline: October 3rd 2022

• Submission site: https://openreview.net/group?id=NeurIPS.cc/2022/Workshop/DeepRL 

• Call for Papers & formatting instruction: [link]

• Call for Opinion Talk Abstracts: [link]

• Financial Support Form: [link]

• Q&A: deeprl.workshop.neurips2022@gmail.com  

• Workshop date: December 9th 2022

• Workshop Time: 8:25am - 5:30pm PST

Invited Speakers

Schedule (December 9th 2022, 8:25am-5:30pm PST)

• 08:25 - 08:30    Welcome and Introduction 

• 08:30 - 09:00    Invited Talk - Tobias Gerstenberg - A counterfactual simulation model of causal judgments about social agents

• 09:00 - 09:15    Contributed talk - Escher: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regret - Stephen Marcus McAleer, Gabriele Farina, Marc Lanctot, Tuomas Sandholm

• 09:15 - 09:30    Contributed talk - Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training - Yecheng Jason Ma, Shagun Sodhani, Dinesh Jayaraman, Osbert Bastani, Vikash Kumar, Amy Zhang

• 09:30 - 09:45    Contributed talk - Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function - Ruijie Zheng, Xiyao Wang, Huazhe Xu, Furong Huang

• 09:45 - 10:00    Contributed talk - Offline Q-learning on Diverse Multi-Task Data Both Scales And Generalizes - Aviral Kumar, Rishabh Agarwal, Xinyang Geng, George Tucker, Sergey Levine [Best Paper Runner Up Award]

• 10:00 - 10:30    Invited Talk - Jakob Foerster - Opponent-Shaping and Interference in General-Sum Games

• 10:30 - 11:00    BREAK

• 11:00 - 11:30    Opinion Contributed Talk - Scott Jordan - Scientific Experiments in Reinforcement Learning

• 11:30 - 11:45    Contributed talk - Transformers are Sample-Efficient World Models - Vincent Micheli, Eloi Alonso, François Fleuret [Best Paper Award]

• 11:45 - 12:00    Contributed talk - Scaling Laws for a Multi-Agent Reinforcement Learning Model - Oren Neumann, Claudius Gros

• 12:00 - 12:30    Opinion Contributed Talk - Natasha Jaques - The need for social learning in RL

• 12:30 - 13:30    Poster session [Lunch]

• 13:30 - 14:00    Opinion Contributed Talk - Stephanie Chan - The World is not Uniformly Distributed; Important Implications for Deep RL

• 14:00 - 14:30    Invited Talk - Amy Zhang - Learning Generalist Agents

• 14:30 - 15:00    BREAK

• 15:00 - 15:30    Invited Talk - Igor Mordatch - Connections Between Sequence Modeling and Reinforcement Learning

• 15:30 - 15:45    Deep RL Implementation Talk - John Schulman - PPO

• 15:45 - 16:00    Deep RL Implementation Talk - Danijar Hafner - Dreamer

• 16:00 - 16:15    Deep RL Implementation Talk - Kristian Hartikainen - SAC

• 16:15 - 16:30    Deep RL Implementation Talk - Aviral Kumar, Ilya Kostrikov - CQL + Real Quadruped Walking from Scratch

• 16:30 - 17:30    Panel discussion - Stephanie Chan, Jakob Foerster, Tobias Gerstenberg, Scott Jordan, Igor Mordatch, Natasha Jaques

Organizers

Advisory Board

Accepted Papers

• Toward Causal-Aware RL: State-Wise Action-Refined Temporal Difference slideslive

Hao Sun, Taiyi Wang

• Novel Policy Seeking with Constrained Optimization slideslive

Hao Sun, Zhenghao Peng, Bo Dai, Dahua Lin, Bolei Zhou

• MOPA: a Minimalist Off-Policy Approach to Safe-RL slideslive

Hao Sun, Ziping Xu, Zhenghao Peng, Meng Fang, Bo Dai, Bolei Zhou

• Supervised Q-Learning for Continuous Control slideslive

Hao Sun, Ziping Xu, Taiyi Wang, Meng Fang, Bolei Zhou

• Automated Dynamics Curriculums for Deep Reinforcement Learning

Sean L Metzger

• Learning Successor Feature Representations to Train Robust Policies for Multi-task Learning

Melissa Mozifian, Dieter Fox, David Meger, Fabio Ramos, Animesh Garg

• Inducing Functions through Reinforcement Learning without Task Specification slideslive

Junmo Cho, Donghwan Lee, Young-Gyu Yoon

• Biological Neurons vs Deep Reinforcement Learning: Sample efficiency in a simulated game-world slideslive

Forough Habibollahi, Moein Khajehnejad, Amitesh Gaurav, Brett Joseph Kagan

• Robust Option Learning for Compositional Generalization

Kishor Jothimurugan, Steve Hsu, Osbert Bastani, Rajeev Alur

• Reinforcement Learning in System Identification slideslive

Jose Antonio Martin H., Oscar Fernández Vicente, Sergio Perez, Anas Belfadil, Cristina Ibanez-Llano, Freddy José Perozo Rondón, Jose Javier Valle, Javier Arechalde Pelaz

• Value-based CTDE Methods in Symmetric Two-team Markov Game: from Cooperation to Team Competition slideslive

Pascal Leroy, Jonathan Pisane, Damien Ernst

• Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective slideslive

Raj Ghugare, Homanga Bharadhwaj, Benjamin Eysenbach, Sergey Levine, Russ Salakhutdinov

• A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning slideslive

Zixiang Chen, Chris Junchi Li, Angela Yuan, Quanquan Gu, Michael Jordan

• PCRL: Priority Convention Reinforcement Learning for Microscopically Sequencable Multi-agent Problems

Xing Zhou, Hao Gao, Xin Xu, Xinglong Zhang, Hongda Jia, Dongzi Wang

• Prioritizing Samples in Reinforcement Learning with Reducible Loss

Shiva Kanth Sujit, Somjit Nath, Pedro Braga, Samira Ebrahimi Kahou

• Sample-efficient Adversarial Imitation Learning slideslive

Dahuin Jung, Hyungyu Lee, Sungroh Yoon

• Locally Constrained Representations in Reinforcement Learning slideslive

Somjit Nath, Samira Ebrahimi Kahou

• Guided Skill Learning and Abstraction for Long-Horizon Manipulation slideslive

Shuo Cheng, Danfei Xu

• Planning Immediate Landmarks of Targets for Model-Free Skill Transfer across Agents

Minghuan Liu, Zhengbang Zhu, Menghui Zhu, Yuzheng Zhuang, Weinan Zhang, Jianye HAO

• Variance Reduction in Off-Policy Deep Reinforcement Learning using Spectral Normalization slideslive

Payal Bawa, Rafael Oliveira, Fabio Ramos

• Pretraining the Vision Transformer using self-supervised methods for vision based Deep Reinforcement Learning

Manuel Goulão, Arlindo L. Oliveira

• Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning slideslive

Matthias Gerstgrasser, Tom Danino, Sarah Keren

• Improving Assistive Robotics with Deep Reinforcement Learning

Yash Jakhotiya, Iman Haque

• PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm slideslive

Toygun Basaklar, Suat Gumussoy, Umit Ogras

• Imitation from Observation With Bootstrapped Contrastive Learning

Medric Sonwa, Johanna Hansen, Eugene Belilovsky

• Learning Semantics-Aware Locomotion Skills from Human Demonstrations slideslive

Yuxiang Yang, Xiangyun Meng, Wenhao Yu, Tingnan Zhang, Jie Tan, Byron Boots

• BLaDE: Robust Exploration via Diffusion Models slideslive

Bilal Piot, Zhaohan Daniel Guo, Shantanu Thakoor, Mohammad Gheshlaghi Azar

• Rewarding Episodic Visitation Discrepancy for Exploration in Reinforcement Learning slideslive

Mingqi Yuan, Bo Li, Xin Jin, Wenjun Zeng

• Co-Imitation: Learning Design and Behaviour by Imitation slideslive

Chang Rajani, Karol Arndt, David Blanco-Mulero, Kevin Sebastian Luck, Ville Kyrki

• Transformers are Sample-Efficient World Models slideslive

Vincent Micheli, Eloi Alonso, François Fleuret

• Training Graph Neural Networks with Policy Gradients to Perform Tree Search slideslive

Matthew Macfarlane, Diederik M Roijers, Herke van Hoof

• The Benefits of Model-Based Generalization in Reinforcement Learning slideslive

Kenny John Young, Aditya Ramesh, Louis Kirsch, Jürgen Schmidhuber

• A Connection between One-Step Regularization and Critic Regularization in Reinforcement Learning slideslive

Benjamin Eysenbach, Matthieu Geist, Ruslan Salakhutdinov, Sergey Levine

• On All-Action Policy Gradients slideslive

Michal Nauman, Marek Cygan

• Do As You Teach: A Multi-Teacher Approach to Self-Play in Deep Reinforcement Learning slideslive

Chaitanya Kharyal, Tanmay Kumar Sinha, SaiKrishna Gottipati, Srijita Das, Matthew E. Taylor

• Converging to Unexploitable Policies in Continuous Control Adversarial Games slideslive

Maxwell Goldstein, Noam Brown

• Model and Method: Training-Time Attack for Cooperative Multi-Agent Reinforcement Learning

Siyang Wu, Tonghan Wang, Xiaoran Wu, Jingfeng Zhang, Yujing Hu, Changjie Fan, Chongjie Zhang

• Actor Prioritized Experience Replay slideslive

Baturay Saglam, Furkan Burak Mutlu, Doğan Can Çiçek, Suleyman Serdar Kozat

• DRL-EPANET: Deep reinforcement learning for optimal control at scale in Water Distribution Systems slideslive

Anas Belfadil, David Modesto, Jose Antonio Martin H.

• Hypernetwork-PPO for Continual Reinforcement Learning slideslive

Philemon Schöpf, Sayantan Auddy, Jakob Hollenstein, Antonio Rodriguez-sanchez

• Dynamic Collaborative Multi-Agent Reinforcement Learning Communication for Autonomous Drone Reforestation slideslive

Philipp Dominic Siedler

• SoftTreeMax: Policy Gradient with Tree Search slideslive

Gal Dalal, Assaf Hallak, Shie Mannor, Gal Chechik

• Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement slideslive

Michael Chang, Alyssa Li Dayan, Franziska Meier, Thomas L. Griffiths, Sergey Levine, Amy Zhang

• Constrained Imitation Q-learning with Earth Mover’s Distance reward slideslive

Wenyan Yang, Nataliya Strokina, Joni Pajarinen, Joni-kristian Kamarainen

• Concept-based Understanding of Emergent Multi-Agent Behavior slideslive

Niko Grupen, Natasha Jaques, Been Kim, Shayegan Omidshafiei

• Perturbed Quantile Regression for Distributional Reinforcement Learning slideslive

Tae Hyun Cho, Seungyub Han, Heesoo Lee, Kyungjae Lee, Jungwoo Lee

• Understanding Hindsight Goal Relabeling Requires Rethinking Divergence Minimization

Lunjun Zhang, Bradly C. Stadie

• The Surprising Effectiveness of Latent World Models for Continual Reinforcement Learning slideslive

Samuel Kessler, Piotr Miłoś, Jack Parker-Holder, Stephen J. Roberts

• Distributional deep Q-learning with CVaR regression slideslive

Mastane Achab, Reda ALAMI, YASSER ABDELAZIZ DAHOU DJILALI, Kirill Fedyanin, Eric Moulines, Maxim Panov

• Implicit Offline Reinforcement Learning via Supervised Learning

Alexandre Piché, Rafael Pardinas, David Vazquez, Igor Mordatch, Igor Mordatch, Christopher Pal

• A Ranking Game for Imitation Learning slideslive

Harshit Sikchi, Akanksha Saran, Wonjoon Goo, Scott Niekum

• Momentum Boosted Episodic Memory for Improving Learning in Long-Tailed RL Environments slideslive

Dolton Milagres Fernandes, Pramod Kaushik, Harsh Shukla, Bapi Raju Surampudi

• Toward Effective Deep Reinforcement Learning for 3D Robotic Manipulation: Multimodal End-to-End Reinforcement Learning from Visual and Proprioceptive Feedback

Samyeul Noh, Hyun Myung

• Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learning slideslive

Mhairi Dunion, Trevor McInroe, Kevin Sebastian Luck, Josiah P. Hanna, Stefano V Albrecht

• Learning a Domain-Agnostic Policy through Adversarial Representation Matching for Cross-Domain Policy Transfer slideslive

Hayato Watahiki, Ryo Iwase, Ryosuke Unno, Yoshimasa Tsuruoka

• Memory-Efficient Reinforcement Learning with Priority based on Surprise and On-policyness slideslive

Ryosuke Unno, Yoshimasa Tsuruoka

• Visual Imitation Learning with Patch Rewards

Minghuan Liu, Tairan He, Weinan Zhang, Shuicheng YAN, Zhongwen Xu

• Evaluating Long-Term Memory in 3D Mazes

Jurgis Pašukonis, Timothy P Lillicrap, Danijar Hafner

• Pink Noise Is All You Need: Colored Noise Exploration in Deep Reinforcement Learning slideslive

Onno Eberhard, Jakob Hollenstein, Cristina Pinneri, Georg Martius

• MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning slideslive

Mikayel Samvelyan, Akbir Khan, Michael D Dennis, Minqi Jiang, Jack Parker-Holder, Jakob Nicolaus Foerster, Roberta Raileanu, Tim Rocktäschel

• CASA: Bridging the Gap between Policy Improvement and Policy Evaluation with Conflict Averse Policy Iteration slideslive

Changnan Xiao, Haosen Shi, Jiajun Fan, Shihong Deng, Haiyan Yin

• Contrastive Value Learning: Implicit Models for Simple Offline RL slideslive

Bogdan Mazoure, Benjamin Eysenbach, Ofir Nachum, Jonathan Tompson

• Transformer-based World Models Are Happy With 100k Interactions slideslive

Jan Robine, Marc Höftmann, Tobias Uelwer, Stefan Harmeling

• Graph Q-Learning for Combinatorial Optimization slideslive

Victoria Magdalena Dax, Jiachen Li, Kevin Leahy, Mykel Kochenderfer

• Scaling Laws for a Multi-Agent Reinforcement Learning Model slideslive

Oren Neumann, Claudius Gros

• VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training slideslive

Yecheng Jason Ma, Shagun Sodhani, Dinesh Jayaraman, Osbert Bastani, Vikash Kumar, Amy Zhang

• Language Models Can Teach Themselves to Program Better slideslive

Patrick Haluptzok, Matthew Bowers, Adam Tauman Kalai

• Uncertainty-Driven Exploration for Generalization in Reinforcement Learning

Yiding Jiang, J Zico Kolter, Roberta Raileanu

• Distance-Sensitive Offline Reinforcement Learning slideslive

Jianxiong Li, Xianyuan Zhan, Haoran Xu, Xiangyu Zhu, Jingjing Liu, Ya-Qin Zhang

• Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function slideslive

Ruijie Zheng, Xiyao Wang, Huazhe Xu, Furong Huang

• Emergent collective intelligence from massive-agent cooperation and competition slideslive

Hanmo Chen, Stone Tao, Jiaxin Chen, Weihan Shen, Xihui Li, Sikai Cheng, Xiaolong Zhu, Xiu Li

• Efficient Offline Policy Optimization with a Learned Model slideslive

Zichen Liu, Siyi Li, Wee Sun Lee, Shuicheng YAN, Zhongwen Xu

• Giving Robots a Hand: Broadening Generalization via Hand-Centric Human Video Demonstrations

Moo Jin Kim, Jiajun Wu, Chelsea Finn

• Choreographer: Learning and Adapting Skills in Imagination slideslive

Pietro Mazzaglia, Tim Verbelen, Bart Dhoedt, Alexandre Lacoste, Sai Rajeswar

• Efficient Exploration using Model-Based Quality-Diversity with Gradients slideslive

Bryan Lim, Manon Flageat, Antoine Cully

• Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning slideslive

Zhendong Wang, Jonathan J Hunt, Mingyuan Zhou

• Investigating Multi-task Pretraining and Generalization in Reinforcement Learning

Adrien Ali Taiga, Rishabh Agarwal, Jesse Farebrother, Aaron Courville, Marc G Bellemare

• Hyperbolic Deep Reinforcement Learning slideslive

Edoardo Cetin, Benjamin Paul Chamberlain, Michael M. Bronstein, Jonathan J Hunt

• Multi-Source Transfer Learning for Deep Model-Based Reinforcement Learning

Remo Sasso, Matthia Sabatelli, Marco A. Wiering

• Offline Reinforcement Learning for Customizable Visual Navigation

Dhruv Shah, Arjun Bhorkar, Hrishit Leen, Ilya Kostrikov, Nicholas Rhinehart, Sergey Levine

• GNM: A General Navigation Model to Drive Any Robot

Dhruv Shah, Ajay Sridhar, Arjun Bhorkar, Noriaki Hirose, Sergey Levine

• Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning slideslive

Anton Bakhtin, David J Wu, Adam Lerer, Jonathan Gray, Athul Paul Jacob, Gabriele Farina, Alexander H Miller, Noam Brown

• Towards True Lossless Sparse Communication in Multi-Agent Systems slideslive

Seth Karten, Mycal Tucker, Siva Kailas, Katia P. Sycara

• SPRINT: Scalable Semantic Policy Pre-training via Language Instruction Relabeling

Jesse Zhang, Karl Pertsch, Jiahui Zhang, Taewook Nam, Sung Ju Hwang, Xiang Ren, Joseph J Lim

• On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning slideslive

Yifan Xu, Nicklas Hansen, Zirui Wang, Yung-Chieh Chan, Hao Su, Zhuowen Tu

• Adversarial Cheap Talk

Chris Lu, Timon Willi, Alistair Letcher, Jakob Nicolaus Foerster

• Simple Emergent Action Representations from Multi-Task Policy Training slideslive

Pu Hua, Yubei Chen, Huazhe Xu

• Graph Inverse Reinforcement Learning from Diverse Videos slideslive

Sateesh Kumar, Jonathan Zamora, Nicklas Hansen, Rishabh Jangir, Xiaolong Wang

• Scaling up and Stabilizing Differentiable Planning with Implicit Differentiation slideslive

Linfeng Zhao, Huazhe Xu, Lawson L.S. Wong

• ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regret slideslive

Stephen Marcus McAleer, Gabriele Farina, Marc Lanctot, Tuomas Sandholm

• MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations slideslive

Nicklas Hansen, Yixin Lin, Hao Su, Xiaolong Wang, Vikash Kumar, Aravind Rajeswaran

• Time-Myopic Go-Explore: Learning A State Representation for the Go-Explore Paradigm slideslive

Marc Höftmann, Jan Robine, Stefan Harmeling

• In-context Reinforcement Learning with Algorithm Distillation slideslive

Michael Laskin, Luyu Wang, Junhyuk Oh, Emilio Parisotto, Stephen Spencer, Richie Steigerwald, DJ Strouse, Steven Stenberg Hansen, Angelos Filos, Ethan Brooks, Maxime Gazeau, Himanshu Sahni, Satinder Singh, Volodymyr Mnih

• Learning Representations for Reinforcement Learning with Hierarchical Forward Models slideslive

Trevor McInroe, Lukas Schäfer, Stefano V Albrecht

• Skill Machines: Temporal Logic Composition in Reinforcement Learning slideslive

Geraud Nangue Tasse, Devon Jarvis, Steven James, Benjamin Rosman

• Building a Subspace of Policies for Scalable Continual Learning slideslive

Jean-Baptiste Gaya, Thang Doan, Lucas Caccia, Laure Soulier, Ludovic Denoyer, Roberta Raileanu

• One-shot Visual Imitation via Attributed Waypoints and Demonstration Augmentation slideslive

Matthew Chang, Saurabh Gupta

• Visual Reinforcement Learning with Self-Supervised 3D Representations slideslive

Yanjie Ze, Nicklas Hansen, Yinbo Chen, Mohit Jain, Xiaolong Wang

• Multi-skill Mobile Manipulation for Object Rearrangement slideslive

Jiayuan Gu, Devendra Singh Chaplot, Hao Su, Jitendra Malik

• A study of natural robustness of deep reinforcement learning algorithms towards adversarial perturbations slideslive

Qisai Liu, Xian Yeow Lee, Soumik Sarkar

• Contrastive Example-Based Control

Kyle Beltran Hatch, Sarthak J Shetty, Benjamin Eysenbach, Tianhe Yu, Rafael Rafailov, Ruslan Salakhutdinov, Sergey Levine, Chelsea Finn

• Efficient Multi-Task Reinforcement Learning via Selective Behavior Sharing slideslive

Grace Zhang, Ayush Jain, Injune Hwang, Shao-Hua Sun, Joseph J Lim

• VARIATIONAL REPARAMETRIZED POLICY LEARNING WITH DIFFERENTIABLE PHYSICS slideslive

Zhiao Huang, Litian Liang, Zhan Ling, Xuanlin Li, Chuang Gan, Hao Su

• Adversarial Policies Beat Professional-Level Go AIs slideslive

Tony Tong Wang, Adam Gleave, Nora Belrose, Tom Tseng, Michael D Dennis, Yawen Duan, Viktor Pogrebniak, Joseph Miller, Sergey Levine, Stuart Russell

• Sample-Efficient Reinforcement Learning by Breaking the Replay Ratio Barrier

Pierluca D'Oro, Max Schwarzer, Evgenii Nikishin, Pierre-Luc Bacon, Marc G Bellemare, Aaron Courville

• Abstract-to-Executable Trajectory Translation for One-Shot Task Generalization slideslive

Stone Tao, Xiaochen Li, Tongzhou Mu, Zhiao Huang, Yuzhe Qin, Hao Su

• Off-policy Reinforcement Learning with Optimistic Exploration and Distribution Correction slideslive

Jiachen Li, Shuo Cheng, Zhenyu Liao, Huayan Wang, William Yang Wang, Qinxun Bai

• Look Back When Surprised: Stabilizing Reverse Experience Replay for Neural Approximation

Ramnath Kumar, Dheeraj Mysore Nagaraj

• Rethinking Learning Dynamics in RL using Adversarial Networks slideslive

Ramnath Kumar, Tristan Deleu, Yoshua Bengio

• Policy Architectures for Compositional Generalization in Control slideslive

Allan Zhou, Vikash Kumar, Chelsea Finn, Aravind Rajeswaran

• SEM2: Enhance Sample Efficiency and Robustness of End-to-end Urban Autonomous Driving via Semantic Masked World Model slideslive

Zeyu Gao, Yao Mu, Ruoyan Shen, Chen Chen, Yangang Ren, Jianyu Chen, Shengbo Eben Li, Ping Luo, Yanfeng Lu

• Fine-tuning Offline Policies with Optimistic Action Selection slideslive

Max Sobol Mark, Ali Ghadirzadeh, Xi Chen, Chelsea Finn

• AsymQ: Asymmetric Q-loss to mitigate overestimation bias in off-policy reinforcement learning

Qinsheng Zhang, Arjun Krishna, Sehoon Ha, Yongxin Chen

• Cyclophobic Reinforcement Learning slideslive

Stefan Sylvius Wagner, Peter Arndt, Jan Robine, Stefan Harmeling

• Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search slideslive

Michał Zawalski, Michał Tyrolski, Konrad Czechowski, Damian Stachura, Piotr Piękos, Tomasz Odrzygóźdź, Yuhuai Wu, Łukasz Kuciński, Piotr Miłoś

• Quantization-aware Policy Distillation (QPD) slideslive

Thomas Avé, Kevin Mets, Tom De Schepper, Steven Latre

• ERL-Re$^2$: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation

Pengyi Li, Hongyao Tang, Jianye HAO, YAN ZHENG, Xian Fu, Zhaopeng Meng

• EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model slideslive

Yifu Yuan, Jianye HAO, Fei Ni, Yao Mu, YAN ZHENG, Yujing Hu, Jinyi Liu, Yingfeng Chen, Changjie Fan

• Imitating Human Behaviour with Diffusion Models slideslive

Tim Pearce, Tabish Rashid, Anssi Kanervisto, David Bignell, Mingfei Sun, Raluca Georgescu, Sergio Valcarcel Macua, Shan Zheng Tan, Ida Momennejad, Katja Hofmann, Sam Devlin

• A Game-Theoretic Perspective of Generalization in Reinforcement Learning slideslive

Chang Yang, RUIYU WANG, Xinrun Wang, Zhen Wang

• Foundation Models for History Compression in Reinforcement Learning

Fabian Paischer, Thomas Adler, Andreas Radler, Markus Hofmarcher, Sepp Hochreiter

• Multi-Agent Policy Transfer via Task Relationship Modeling slideslive

Rong-Jun Qin, Feng Chen, Tonghan Wang, Lei Yuan, Xiaoran Wu, Yipeng Kang, Zongzhang Zhang, Chongjie Zhang, Yang Yu

• Domain Invariant Q-Learning for model-free robust continuous control under visual distractions slideslive

Tom Dupuis, Jaonary Rabarisoa, Quoc Cuong PHAM, David Filliat

• Guiding Exploration Towards Impactful Actions slideslive

Vaibhav Saxena, Jimmy Ba, Danijar Hafner

• Deep Learning of Intrinsically Motivated Options in the Arcade Learning Environment slideslive

Louis Bagot, Kevin Mets, Tom De Schepper, Steven Latre

• Better state exploration using action sequence equivalence slideslive

Nathan Grinsztajn, Toby Johnstone, Johan Ferret, Philippe Preux

• In the ZONE: Measuring difficulty and progression in curriculum generation slideslive

Rose E Wang, Jesse Mu, Dilip Arumugam, Natasha Jaques, Noah Goodman

• Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-Oriented Dialogue Systems

Yihao Feng, Shentao Yang, Shujian Zhang, Jianguo Zhang, Caiming Xiong, Mingyuan Zhou, Huan Wang

• Variance Double-Down: The Small Batch Size Anomaly in Multistep Deep Reinforcement Learning slideslive

Johan Samir Obando Ceron, Marc G Bellemare, Pablo Samuel Castro

• Offline Reinforcement Learning from Heteroskedastic Data Via Support Constraints

Anikait Singh, Aviral Kumar, quan vuong, Yevgen Chebotar, Sergey Levine

• Pre-Training for Robots: Leveraging Diverse Multitask Data via Offline Reinforcement Learning

Anikait Singh, Aviral Kumar, Frederik Ebert, Yanlai Yang, Chelsea Finn, Sergey Levine

• Efficient Deep Reinforcement Learning Requires Regulating Statistical Overfitting

Qiyang Li, Aviral Kumar, Ilya Kostrikov, Sergey Levine

• Offline Q-learning on Diverse Multi-Task Data Both Scales And Generalizes slideslive

Aviral Kumar, Rishabh Agarwal, Xinyang Geng, George Tucker, Sergey Levine

• Bayesian Q-learning With Imperfect Expert Demonstrations slideslive

Fengdi Che, Xiru Zhu, Doina Precup, David Meger, Gregory Dudek

• Design Process is a Reinforcement Learning Problem slideslive

Reza Kakooee, Benjamin Dillenburger

• Return Augmentation gives Supervised RL Temporal Compositionality slideslive

Keiran Paster, Silviu Pitis, Sheila A. McIlraith, Jimmy Ba

• Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks

Jesse Farebrother, Joshua Greaves, Rishabh Agarwal, Charline Le Lan, Ross Goroshin, Pablo Samuel Castro, Marc G Bellemare

• Human-AI Coordination via Human-Regularized Search and Learning slideslive

Hengyuan Hu, David J Wu, Adam Lerer, Jakob Nicolaus Foerster, Noam Brown

• ABC: Adversarial Behavioral Cloning for Offline Mode-Seeking Imitation Learning slideslive

Eddy Hudson, Ishan Durugkar, Garrett Warnell, Peter Stone

• Deconfounded Imitation Learning slideslive

Risto Vuorio, Pim De Haan, Johann Brehmer, Hanno Ackermann, Daniel Dijkman, Taco Cohen

• Integrating Episodic and Global Bonuses for Efficient Exploration

Mikael Henaff, Minqi Jiang, Roberta Raileanu

• Aggressive Q-Learning with Ensembles: Achieving Both High Sample Efficiency and High Asymptotic Performance slideslive

Yanqiu Wu, Xinyue Chen, Che Wang, Yiming Zhang, Keith W. Ross

• Confidence-Conditioned Value Functions for Offline Reinforcement Learning

Joey Hong, Aviral Kumar, Sergey Levine

• Replay Buffer With Local Forgetting for Adaptive Deep Model-Based Reinforcement Learning slideslive

Ali Rahimi-Kalahroudi, Janarthanan Rajendran, Ida Momennejad, Harm van Seijen, Sarath Chandar

• A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games

Samuel Sokota, Ryan D'Orazio, J Zico Kolter, Nicolas Loizou, Marc Lanctot, Ioannis Mitliagkas, Noam Brown, Christian Kroer

• Training Equilibria in Reinforcement Learning

Lauro Langosco, David Krueger, Adam Gleave

• Feasible Adversarial Robust Reinforcement Learning for Underspecified Environments

John Banister Lanier, Stephen Marcus McAleer, Pierre Baldi, Roy Fox

• Real World Offline Reinforcement Learning with Realistic Data Source

Gaoyue Zhou, Liyiming Ke, Siddhartha Srinivasa, Abhinav Gupta, Aravind Rajeswaran, Vikash Kumar

• Ensemble-based Uncertainty Estimation with overlapping alternative Predictions

Dirk Eilers, Felippe Schmoeller Roza, Karsten Roscher

• A Framework for Predictable Actor-Critic Control slideslive

Josiah D Coad, James Ault, Jeff Hykin, Guni Sharon

• Train Offline, Test Online: A Real Robot Learning Benchmark slideslive

Gaoyue Zhou, Victoria Dean, Mohan Kumar Srirama, Aravind Rajeswaran, Jyothish Pari, Kyle Beltran Hatch, Aryan Jain, Tianhe Yu, Pieter Abbeel, Lerrel Pinto, Chelsea Finn, Abhinav Gupta

• Curiosity in Hindsight

Daniel Jarrett, Corentin Tallec, Florent Altché, Thomas Mesnard, Remi Munos, Michal Valko

• What Makes Certain Pre-Trained Visual Representations Better for Robotic Learning?

Kyle Hsu, Tyler Ga Wei Lum, Ruohan Gao, Shixiang Shane Gu, Jiajun Wu, Chelsea Finn

• Unleashing The Potential of Data Sharing in Ensemble Deep Reinforcement Learning slideslive

Zhixuan Lin, Pierluca D'Oro, Evgenii Nikishin, Aaron Courville

• Revisiting Bellman Errors for Offline Model Selection

Joshua P Zitovsky, Daniel de Marchi, Rishabh Agarwal, Michael Rene Kosorok

• Temporary Goals for Exploration slideslive

Haoyang Xu, Jimmy Ba, Silviu Pitis, Harris Chan

• On The Fragility of Learned Reward Functions slideslive

Lev E McKinney, Yawen Duan, David Krueger, Adam Gleave

• Policy Aware Model Learning via Transition Occupancy Matching slideslive

Yecheng Jason Ma, Kausik Sivakumar, Osbert Bastani, Dinesh Jayaraman

• Scaling Covariance Matrix Adaptation MAP-Annealing to High-Dimensional Controllers slideslive

Bryon Tjanaka, Matthew Christopher Fontaine, Aniruddha Kalkar, Stefanos Nikolaidis

• Learning Exploration Policies with View-based Intrinsic Rewards slideslive

Yijie Guo, Yao Fu, Run Peng, Honglak Lee

• The Emphatic Approach to Average-Reward Policy Evaluation slideslive

Jiamin He, Yi Wan, A. Rupam Mahmood

• CLUTR: Curriculum Learning via Unsupervised Task Representation Learning slideslive

Abdus Salam Azad, Izzeddin Gur, Aleksandra Faust, Pieter Abbeel, Ion Stoica

• Generalizable Point Cloud Reinforcement Learning for Sim-to-Real Dexterous Manipulation

Yuzhe Qin, Binghao Huang, Zhao-Heng Yin, Hao Su, Xiaolong Wang

• InfODist: Online distillation with Informative rewards improves generalization in Curriculum Learning

Rahul Siripurapu, Vihang Prakash Patil, Kajetan Schweighofer, Marius-Constantin Dinu, Thomas Schmied, Luis Eduardo Ferro Diez, Markus Holzleitner, Hamid Eghbal-zadeh, Michael K Kopp, Sepp Hochreiter

• Towards A Unified Policy Abstraction Theory and Representation Learning Approach in Markov Decision Processes slideslive

Min Zhang, Hongyao Tang, Jianye HAO, YAN ZHENG

• Noisy Symbolic Abstractions for Deep RL: A case study with Reward Machines slideslive

Andrew C Li, Zizhao Chen, Pashootan Vaezipoor, Toryn Q. Klassen, Rodrigo Toro Icarte, Sheila A. McIlraith

• Lagrangian Model Based Reinforcement Learning slideslive

Adithya Ramesh, Balaraman Ravindran

• Analyzing the Sensitivity to Policy-Value Decoupling in Deep Reinforcement Learning Generalization slideslive

Nasik Muhammad Nafi, Raja Farrukh Ali, William Hsu

• Efficient Multi-Horizon Learning for Off-Policy Reinforcement Learning

Raja Farrukh Ali, Nasik Muhammad Nafi, Kevin Duong, William Hsu

• VI$^2$N: A Network for Planning Under Uncertainty based on Value of Information

Samantha Johnson, Michael A Buice, Koosha Khalvati

• Neural All-Pairs Shortest Path for Reinforcement Learning

Cristina Pinneri, Georg Martius, Andreas Krause

• Learning Dexterous Manipulation from Exemplar Object Trajectories and Pre-Grasps

Sudeep Dasari, Abhinav Gupta, Vikash Kumar

• Composing Task Knowledge with Modular Successor Feature Approximators

Wilka Torrico Carvalho, Angelos Filos, Richard Lewis, Honglak Lee, Satinder Singh