Accepted Papers
Spotlights
Differentiable Quality Diversity for Reinforcement Learning by Approximating Gradients
Bryon Tjanaka, Matthew Christopher Fontaine, Julian Togelius, Stefanos Nikolaidis
Walk the Random Walk: Learning to Discover and Reach Goals Without Supervision
Lina Mezghani, Piotr Bojanowski, Karteek Alahari, Sainbayar Sukhbaatar
DSA-ME: Deep Surrogate Assisted MAP-Elites
Yulun Zhang, Matthew Christopher Fontaine, Amy K Hoover, Stefanos Nikolaidis
Towards Evaluating Adaptivity of Model-Based Reinforcement Learning Methods
Yi Wan, Ali Rahimi-Kalahroudi, Janarthanan Rajendran, Ida Momennejad, Sarath Chandar, Harm van Seijen
Don't Freeze Your Embedding: Lessons from Policy Finetuning in Environment Transfer
Victoria Dean, Daniel Kenji Toyama, Doina Precup
Accelerated Quality-Diversity for Robotics through Massive Parallelism
Bryan Lim, Maxime Allard, Luca Grillotti, Antoine Cully
Posters
Open-Ended Reinforcement Learning with Neural Reward Functions
Robert Meier, Asier Mujika
Streaming Inference for Infinite Non-Stationary Clustering
Rylan Schaeffer, Gabrielle Kaili-May Liu, Yilun Du, Scott Linderman, Ila R Fiete
Watts: Infrastructure for Open-Ended Learning
Aaron Dharna, Charlie Summers, Rohin Dasari, Julian Togelius, Amy K Hoover
Meta-Gradients in Non-Stationary Environments
Jelena Luketina, Sebastian Flennerhag, Yannick Schroecker, David Abel, Tom Zahavy, Satinder Singh
SkillHack: A Benchmark for Skill Transfer in Open-Ended Reinforcement Learning
Michael Matthews, Mikayel Samvelyan, Jack Parker-Holder, Edward Grefenstette, Tim Rocktäschel
Ensemble Learning as a Peer Process
Ehsan Beikihassan, Ali Parviz, Amy K Hoover, Ioannis Koutis
Model-Value Inconsistency as a Signal for Epistemic Uncertainty
Angelos Filos, Eszter Vértes, Zita Marinho, Gregory Farquhar, Diana L Borsa, Abram L. Friesen, Feryal Behbahani, Tom Schaul, Andre Barreto, Simon Osindero
Specialization and Exchange in Neural MMO
Joseph Suarez, Phillip Isola
Bayesian Generational Population-Based Training
Xingchen Wan, Cong Lu, Jack Parker-Holder, Philip J. Ball, Vu Nguyen, Binxin Ru, Michael Osborne
Learning Object-Centered Autotelic Behaviors with Graph Neural Networks
Ahmed Akakzia, Olivier Sigaud
Neuroevolution of Recurrent Architectures on Control Tasks
Maximilien Le Clei, Pierre Bellec
Mixture-of-Variational-Experts for Continual Learning
Heinke Hihn, Daniel Alexander Braun
Diversity Policy Gradient for Sample Efficient Quality-Diversity Optimization
Thomas Pierrot, Valentin Macé, Felix Chalumeau, Arthur Flajolet, Geoffrey Cideron, Karim Beguir, Antoine Cully, Olivier Sigaud, Nicolas Perrin-Gilbert
A little taxonomy of open-endedness
Asiiah Song
When to Go, and When to Explore: The Benefit of Post-Exploration in Intrinsic Motivation
Zhao Yang, Thomas M. Moerland, Mike Preuss, Aske Plaat
Zero-Shot Reward Specification via Grounded Natural Language
Parsa Mahmoudieh, Deepak Pathak, Trevor Darrell
Agent, do you see it now? systematic generalisation in deep reinforcement learning
Borja G. León, Murray Shanahan, Francesco Belardinelli
Backdoors Stuck At The Frontdoor: Multi-Agent Backdoor Attacks That Backfire
Siddhartha Datta, Nigel Shadbolt
A Study of Off-Policy Learning in Environments with Procedural Content Generation
Andy Ehrenberg, Robert Kirk, Minqi Jiang, Edward Grefenstette, Tim Rocktäschel
Subjective Learning for Conflicting Data
Tianren Zhang, Yizhou Jiang, Xin Su, Shangqi Guo, Chongkai Gao, Feng Chen
Learning to Walk Autonomously via Reset-Free Quality-Diversity
Bryan Lim, Alexander Reichenbach, Antoine Cully
On Credit Assignment in Hierarchical Reinforcement Learning
Joery de Vries, Thomas M. Moerland, Aske Plaat
An Empirical Investigation of Mutual Information Skill Learning
Faisal Mohamed, Benjamin Eysenbach, Russ Salakhutdinov
Meta-World Conditional Neural Processes
Suzan Ece Ada, Emre Ugur
Dojo: A Large Scale Benchmark for Multi-Task Reinforcement Learning
Dominik Schmidt
Generalization Games for Reinforcement Learning
Manfred Diaz, Charlie Gauthier, Glen Berseth, Liam Paull
Discovering Unsupervised Behaviours from Full State Trajectories
Luca Grillotti, Antoine Cully