Long-Fei Li

dynamic regret (4) reinforcement learning (3) online learning (3) linear mixture mdp (3) unknown transition (2) policy optimization (2) regret bound (2) linear function approximation (2) adversarial reward (2) markov decision process (2) transition kernel (1) non-stationary environment (1) adversarial reinforcement learning (1) least squares estimation (1) non-stationary mdp (1) model-based rl (1) online markov decision process (1) adversarial markov decision process (1) adversarial learning (1) function approximation (1)