Qinbo Bai

constrained markov decision process (6) sample complexity (3) policy gradient (2) regret bound (2) markov decision process (2) zero constraint violation (2) average reward (2) primal-dual algorithm (2) reinforcement learning (2) constraint violation (2) multi-objective optimization (1) zero-sum game (1) bandit optimization (1) primal-dual method (1) multi-objective reinforcement learning (1) model-free algorithm (1) peak constraint (1) posterior sampling algorithm (1) regret bound analysis (1) long-term average constraint (1)