Yuhao Ding

policy optimization (5) safe reinforcement learning (4) dynamic regret (3) primal-dual optimization (3) constrained markov decision process (3) markov decision process (2) primal-dual method (2) non-stationary environment (2) convergence analysis (2) policy gradient (2) convergence guarantee (2) utility optimization (1) convex optimization (1) sample complexity (1) manifold learning (1) reinforcement learning (1) correlation decay (1) random search (1) mirror descent (1) global convergence (1)