Woojun Kim

multi-agent reinforcement learning (3) deep reinforcement learning (2) visual observation (1) offline reinforcement learning (1) policy learning (1) imitation learning (1) ensemble learning (1) entropy regularization (1) feature extraction (1) supervised learning (1) domain adaptation (1) value function (1) value iteration (1) safe reinforcement learning (1) sample efficiency (1) exploration strategy (1) value factorization (1) sparse reward (1) adaptive exploration (1) reinforcement learning (1)