Anton Raichuk

continuous control (3) imitation learning (3) reinforcement learning (3) policy learning (2) value iteration (1) kullback-leibler divergence (1) reward function (1) off-policy learning (1) hyperparameter tuning (1) entropy regularization (1) game ai (1) game environment (1) expert demonstration (1) adversarial imitation learning (1) deep rl (1) discrete action (1) human demonstration (1) hyperparameter selection (1) action quantization (1) reinforcement learning environment (1)