Richard L. Lewis

reinforcement learning (6) auxiliary task (2) reward function (2) general value function (2) representation learning (2) action-conditional prediction (2) transfer learning (1) in-context learning (1) imitation learning (1) knowledge transfer (1) self-supervised learning (1) deep learning (1) markov decision process (1) game playing (1) few-shot learning (1) policy improvement (1) video prediction (1) state representation (1) reward design (1) policy iteration (1)