Edward S. Hu

Reinforcement Learning (6) Artificial Intelligence (5) Applications (5) Core AI (5) Methods (5) Deep Learning (1) Machine Learning (1) Natural Language Processing (1) Robotics (1) Application Areas (1) Architectures (1) Capabilities (1) Generation (1) Learning Paradigms (1) Learning Types (1)

reinforcement learning (4) imitation learning (2) robot manipulation (2) world model (2) sequential decision making (1) policy learning (1) robot learning (1) belief state (1) continuous control (1) model-based reinforcement learning (1) reward function (1) exploration policy (1) sensory information (1) next-token prediction (1) goal-conditioned reinforcement learning (1) model-based control (1) skill composition (1) reward estimation (1) skill transfer (1) sampling-based planning (1)