Mark K Ho

reinforcement learning (3) task specification (2) imitation learning (2) reward function (2) human-in-the-loop learning (1) inverse reinforcement learning (1) bayesian model (1) distribution shift (1) optimal policy (1) reward learning (1) learning from demonstration (1) contextual bandit (1) policy adaptation (1) value alignment (1) social learning (1) multi-agent coordination (1) reward inference (1) human-agent interaction (1) adversarial game (1) pedagogical behavior (1)