A key theme in the past decade has been that when large neural networks ...
KL-regularized reinforcement learning from expert demonstrations has pro...
Modern AAA video games feature huge game levels and maps which are
incre...
Reinforcement learning (RL) offers the potential for training generally
...
Offline reinforcement learning has shown great promise in leveraging lar...
Offline reinforcement learning enables agents to leverage large pre-coll...
Reinforcement learning from large-scale offline datasets provides us wit...
High-dimensional black-box optimisation remains an important yet notorio...