Shixiang (Shane) Gu

offline reinforcement learning (3) continuous control (3) deep reinforcement learning (3) hierarchical reinforcement learning (3) sample efficiency (2) instruction following (2) off-policy learning (2) sequential monte carlo (2) multi-task learning (1) sim-to-real transfer (1) multi-agent reinforcement learning (1) maximum entropy (1) variational inference (1) ensemble learning (1) imitation learning (1) nonparametric bayesian (1) zero-shot learning (1) embedding learning (1) weakly supervised learning (1) uncertainty quantification (1)