Adrià Puigdomènech Badia

deep reinforcement learning (6) neural network (3) episodic memory (2) value function (2) offline reinforcement learning (1) working memory (1) representation learning (1) experience replay (1) sample efficiency (1) state representation (1) model-based reinforcement learning (1) atari game (1) algorithmic reasoning (1) memory system (1) exploratory policy (1) model-free reinforcement learning (1) behavior policy (1) graph algorithm (1) dynamic programming (1) reinforcement learning (1)