Filippo Lazzati

inverse reinforcement learning (3) reward function (2) markov decision process (2) sample complexity (1) pac learning (1) reward function estimation (1) minimax lower bound (1) linear mdp (1) reward-free exploration (1) feasible reward set (1) linear markov decision process (1) feasible set (1) sample efficiency (1) finite-horizon planning (1) offline reinforcement learning (1) policy optimization (1)