Xiaoyang Tan

offline reinforcement learning (4) trust region (3) multi-agent reinforcement learning (2) advantage learning (2) temporal difference (2) proximal policy optimization (2) action gap (2) reinforcement learning (2) belief propagation (1) density estimation (1) sample efficiency (1) policy gradient (1) feature extraction (1) uncertainty quantification (1) inverse dynamics (1) variational inference (1) robot control (1) value function approximation (1) policy optimization (1) partially observable markov decision process (1)