Ruo Yu Tao

representation learning (1) reinforcement learning (1) temporal difference learning (1) markov decision process (1) information theoretic (1) state representation (1) partial observability (1) temporal difference (1) state representation learning (1) recurrent neural network (1) sparse reward (1) intrinsic reward (1) lambda discrepancy (1) recurrent value network (1) novelty search (1) sample efficient exploration (1)