Lisa Lee

imitation learning (2) sample efficiency (1) knowledge transfer (1) offline reinforcement learning (1) inverse reinforcement learning (1) path planning (1) few-shot learning (1) weakly supervised learning (1) policy learning (1) multitask learning (1) reinforcement learning (1) value iteration (1) continuous control (1) reward function (1) efficient exploration (1) recurrent neural network (1) atari game (1) end-to-end learning (1) representation disentanglement (1) deep reinforcement learning (1)