Mingxuan Jing

policy optimization (2) imitation learning (1) policy learning (1) constrained optimization (1) inverse reinforcement learning (1) model-based reinforcement learning (1) expectation-maximization algorithm (1) trajectory distribution (1) skill learning (1) expert demonstration (1) reward-free learning (1) policy exploration (1) preference-based learning (1) theoretical guarantee (1) exploration efficiency (1) generative adversarial imitation learning (1) option framework (1) imperfect demonstration (1) cost function learning (1) soft constraint (1)