Yuda Song

Reinforcement Learning (1)

model-based reinforcement learning (4) online learning (2) policy optimization (2) representation learning (2) sample complexity (1) model predictive control (1) computational efficiency (1) domain randomization (1) value function (1) real-time processing (1) offline learning (1) target task (1) online reinforcement learning (1) adaptive control (1) regret bound (1) policy adaptation (1) model-free reinforcement learning (1) latent state (1) block mdp (1) source task (1)