Adrien Ecoffet

deep reinforcement learning (2) reinforcement learning (2) imitation learning (2) policy learning (1) language understanding (1) value function (1) reward function (1) off-policy learning (1) optimal policy (1) autonomous agent (1) autonomous vehicle (1) exploration strategy (1) inverse dynamics model (1) dynamics model (1) multi-objective reinforcement learning (1) text-based game (1) behavioral prior (1) moral uncertainty (1) ethical behavior (1) video pretraining (1)