Ramtin Keramati

causal inference (1) robust optimization (1) policy optimization (1) distributional reinforcement learning (1) markov decision process (1) sequential decision (1) unobserved confounding (1) sample-efficient learning (1) risk-sensitive reinforcement learning (1) off-policy policy evaluation (1) conditional value at risk (1) optimism principle (1) risk-sensitive objective (1) distributional bellman operator (1) optimism in uncertainty (1) optimistic policy learning (1)