Tong Mu

reinforcement learning (3) zero-shot learning (1) multi-task learning (1) online learning (1) domain adaptation (1) language grounding (1) distribution shift (1) language learning (1) offline learning (1) domain knowledge (1) distributionally robust optimization (1) preference modeling (1) upper confidence bound (1) contextual bandit (1) reward model (1) meta-reinforcement learning (1) embodied agent (1) policy constraint (1) multi-task generalization (1) large language model (1)