Wanqiao Xu

reinforcement learning (2) regret bound (2) uncertainty quantification (1) policy learning (1) markov decision process (1) regret minimization (1) partial observability (1) conservative policy (1) risk-sensitive reinforcement learning (1) exploration budget (1) conditional value at risk (1) conservative exploration (1) production deployment (1) offline policy (1) deep reinforcement learning (1) tail outcome (1) policy optimization (1)