Chao Tian

regret bound (3) natural policy gradient (2) sample complexity (2) adversarial learning (1) model robustness (1) neural network optimization (1) function approximation (1) kl divergence (1) text generation (1) natural gradient (1) policy learning (1) robust reinforcement learning (1) machine translation (1) markov decision process (1) online learning (1) nash equilibrium (1) natural actor-critic (1) entropy maximization (1) primal-dual algorithm (1) reinforcement learning (1)