Nino Vieillard

reinforcement learning (5) value iteration (3) off-policy learning (2) offline reinforcement learning (2) temporal difference (2) policy regularization (2) deep reinforcement learning (2) function approximation (1) imitation learning (1) sequence modeling (1) inverse reinforcement learning (1) reinforcement learning from human feedback (1) policy learning (1) kullback-leibler divergence (1) minimax optimality (1) kl regularization (1) reward function (1) approximate dynamic programming (1) policy iteration (1) sample complexity (1)