Shane Legg

reward function (4) preference learning (3) inverse reinforcement learning (3) reinforcement learning (2) reward learning (2) deep reinforcement learning (2) value of information (2) human preference (2) multi-task learning (1) attention mechanism (1) q-learning (1) game theory (1) ai safety (1) imitation learning (1) temporal difference learning (1) trajectory optimization (1) sarsa (1) online learning (1) value function estimation (1) value iteration (1)