Jianming HU

offline reinforcement learning (2) sim-to-real transfer (2) domain adaptation (1) robot learning (1) online reinforcement learning (1) sequential modeling (1) goal-conditioned policy (1) embodied agent (1) hybrid learning (1) real-world datum (1) recursive planning (1) sub-goal planning (1) cross-domain policy transfer (1) dynamics-aware policy evaluation (1) goal-conditioned supervised learning (1) dynamics consistency (1) sequential modeling error (1)