Yangchen Pan

reinforcement learning (4) sample efficiency (3) model-based reinforcement learning (2) policy gradient (2) state abstraction (1) online learning (1) continual learning (1) continuous state (1) function approximation (1) domain adaptation (1) supervised learning (1) convergence analysis (1) autonomous driving (1) natural gradient (1) value function (1) optimal control (1) policy optimization (1) distribution shift (1) temporal difference learning (1) multi-agent reinforcement learning (1)