Donghao Ying

constrained markov decision process (2) primal-dual method (2) primal-dual optimization (2) game theory (1) policy gradient (1) convergence analysis (1) utility optimization (1) markov decision process (1) nash equilibrium (1) correlation decay (1) no-regret learning (1) safe reinforcement learning (1) convergence guarantee (1) convergence rate (1) entropy regularization (1) safety constraint (1) actor-critic method (1) constrained mdp (1) dual method (1) general utilities (1)