Philip S. Thomas

off-policy evaluation (9) reinforcement learning (6) variance estimation (3) policy evaluation (3) policy search (3) markov decision process (3) safe policy improvement (2) temporal difference learning (2) behavior policy (2) offline reinforcement learning (2) mean squared error (2) safe reinforcement learning (2) importance sampling (2) counterfactual reasoning (2) sequential decision making (2) policy gradient (2) temporal abstraction (2) natural gradient (2) transfer learning (1) policy optimization (1)