The UCL Deciding, Acting, and Reasoning with Knowledge (DARK) Lab is a Reinforcement Learning research group at the UCL Centre for Artificial Intelligence. We focus on research in complex open-ended environments that provide a constant stream of novel observations without reliable reward functions, often requiring agents to create their own curricula and to deal with external knowledge, natural language, and hard exploration problems.
Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions has been accepted to NeurIPS2021 -- check out our video and Yannic Kilcher's explanation video!
Replay-Guided Adversarial Environment Design has been accepted to NeurIPS2021.
MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research has been accepted to NeurIPS2021.
Tim Rocktäschel has been promoted to Associate Professor.
Prioritized Level Replay has been accepted to ICML2021.
Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning has been accepted to ICML2021.