Lasse Espeholt

reinforcement learning (2) game ai (2) policy gradient (2) multi-task learning (2) deep learning (1) document understanding (1) question answering (1) deep rl (1) reading comprehension (1) machine reading comprehension (1) policy learning (1) value function estimation (1) value estimation (1) autoregressive model (1) atari game (1) deep neural network (1) supervised learning (1) game environment (1) attention mechanism (1) deep reinforcement learning (1)