1

Augmented World Models Facilitate Zero-Shot Dynamics Generalization From A Single Offline Environment
Reinforcement learning from large-scale offline datasets provides us with the ability to learn policies without potentially unsafe or …
Philip J. Ball, Cong Lu, Jack Parker-Holder, Stephen Roberts
Cite arXiv Website PDF
Exploration in Approximate Hyper-State Space for Meta Reinforcement Learning
To rapidly learn a new task, it is often essential for agents to explore efficiently – especially when performance matters from …
Luisa Zintgraf, Leo Feng, Cong Lu, Maximilian Igl, Kristian Hartikainen, Katja Hofmann, Shimon Whiteson
Cite arXiv PDF
On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations
KL-regularized reinforcement learning from expert demonstrations has proved highly successful in improving the sample efficiency of …
Tim G. J. Rudner, Cong Lu, Michael A. Osborne, Yarin Gal, Yee Whye Teh
Cite Website PDF
Revisiting Design Choices in Offline Model Based Reinforcement Learning
Offline reinforcement learning enables agents to make use of large pre-collected datasets of environment transitions and learn control …
Cong Lu, Philip J. Ball, Jack Parker-Holder, Michael A. Osborne, Stephen Roberts
Cite PDF
Think Global and Act Local: Bayesian Optimisation over High-Dimensional Categorical and Mixed Search Spaces
High-dimensional black-box optimisation remains an important yet notoriously challenging problem. Despite the success of Bayesian …
Xingchen Wan, Vu Nguyen, Huong Ha, Binxin Ru, Cong Lu, Michael A. Osborne
Cite arXiv PDF
VariBAD: Variational Bayes-Adaptive Deep RL via Meta-Learning
Trading off exploration and exploitation in an unknown environment is key to maximising expected online return during learning. A …
Luisa Zintgraf, Sebastian Schulze, Cong Lu, Leo Feng, Maximilian Igl, Kyriacos Shiarlis, Yarin Gal, Katja Hofmann, Shimon Whiteson
Cite