Weichao Zhou

Reinforcement Learning (1)

inverse reinforcement learning (2) imitation learning (2) reward function (2) expert demonstration (2) uncertainty quantification (1) symbolic reasoning (1) information retrieval (1) policy learning (1) adversarial training (1) semantic consistency (1) hierarchical bayesian (1) trajectory optimization (1) hierarchical model (1) embedding similarity (1) reward design (1) vision language model (1) task alignment (1) adversarial mechanism (1) global robustness (1) retrieval-augmented generation (1)