Philip Amortila

markov decision process (4) reinforcement learning (4) optimal policy (2) sample efficiency (1) imitation learning (1) policy optimization (1) offline reinforcement learning (1) convergence analysis (1) sample complexity (1) policy learning (1) distributional reinforcement learning (1) policy iteration (1) covariate shift (1) value function (1) value iteration (1) function approximation (1) value function approximation (1) distribution shift (1) off-policy learning (1) robust optimization (1)