
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.
News
-
1/12/2021:
Pasquale Minervini is joining the School of Informatics at the University of Edinburgh as a faculty member in 2022, and he is currently recruiting PhD students!
-
10/10/2021:
Implicit MLE: Backpropagating Through Discrete Exponential Family Distributions has been accepted to NeurIPS2021 -- check out our video and Yannic Kilcher's explanation video!
-
08/10/2021:
Replay-Guided Adversarial Environment Design has been accepted to NeurIPS2021.
-
01/10/2021:
MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research has been accepted to NeurIPS2021.
-
08/07/2021:
Tim Rocktäschel has been promoted to Associate Professor.
-
12/05/2021:
Prioritized Level Replay has been accepted to ICML2021.
-
12/05/2021:
Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning has been accepted to ICML2021.
Faculty
Researchers
PhD Students
Master's Students
Alumni
Hannah Teufel
MSc Student (2021)
