Georgios Theocharous

reinforcement learning (8) seldonian algorithm (2) policy gradient (2) markov decision process (2) online learning (2) action space (2) non-stationary mdp (2) policy optimization (1) distributional reinforcement learning (1) sample efficiency (1) posterior sampling (1) dynamic regret (1) policy learning (1) importance sampling (1) off-policy evaluation (1) batch reinforcement learning (1) sequential decision (1) variance reduction (1) policy improvement (1) sequential hypothesis testing (1)