Ping-Chun Hsieh

reinforcement learning (4) policy optimization (3) regret bound (3) deep reinforcement learning (2) multi-armed bandit (2) adversarial learning (2) neural network (2) global convergence (2) linear bandit (2) markov decision process (1) domain randomization (1) constrained optimization (1) imitation learning (1) exploration-exploitation tradeoff (1) off-policy reinforcement learning (1) policy learning (1) maximum likelihood estimation (1) off-policy learning (1) machine translation (1) reward function (1)