Dylan Hadfield-Menell

reward function (5) inverse reinforcement learning (3) value alignment (3) model debugging (2) reinforcement learning (2) human-robot interaction (2) game theory (1) robotic manipulation (1) multi-agent reinforcement learning (1) robot planning (1) utility optimization (1) imitation learning (1) partially observable markov decision process (1) model misspecification (1) reward design (1) machine learning (1) preference inference (1) reward learning (1) computer vision (1) representation learning (1)