Jingcheng Pang

offline reinforcement learning (1) imitation learning (1) domain adaptation (1) policy learning (1) instruction following (1) hierarchical reinforcement learning (1) regret minimization (1) inverse dynamics (1) off-policy reinforcement learning (1) offline learning (1) natural language (1) robot manipulation (1) expert demonstration (1) experience replay (1) temporal difference error (1) large language model (1) prioritized sampling (1) task language (1) language model rollout (1) goal translation (1)