Yinlam Chow

policy gradient (7) reinforcement learning (6) markov decision process (4) model-based reinforcement learning (4) off-policy evaluation (3) contextual bandit (3) policy optimization (3) conditional value at risk (2) constraint satisfaction (2) regret bound (2) conditional value-at-risk (2) constrained markov decision process (2) sample efficiency (2) importance sampling (2) safe reinforcement learning (2) latent state (2) temporal dynamics (1) markov decision processes (1) variational inference (1) offline reinforcement learning (1)