Tian Xu

imitation learning (4) behavioral cloning (2) model-based reinforcement learning (2) sample complexity (2) adversarial learning (2) reward function (1) distribution shift (1) bellman error (1) value gap (1) adversarial imitation learning (1) reward function optimization (1) near-expert policy (1) reward-free exploration (1) generative adversarial imitation (1) reinforcement learning (1) expert sample complexity (1) function approximation (1) sequential decision making (1) policy learning (1) importance sampling (1)