Hubert Soyer

multi-task learning (2) reinforcement learning (1) policy gradient (1) policy learning (1) deep learning (1) value function estimation (1) value estimation (1) atari game (1) game ai (1) value-based method (1) distributed deep reinforcement learning (1) actor-learner architecture (1) off-policy correction (1) importance weighted (1) population-based training (1) reward normalization (1) value normalization (1) deep reinforcement learning (1) popart normalization (1)