Fan-Ming Luo

Reinforcement Learning (5) Methods (4) Artificial Intelligence (2) Deep Learning (2) Learning Types (2) Machine Learning (1) Robotics (1) Application Areas (1) Applications (1) Architectures (1) Capabilities (1) Core AI (1) Learning Paradigms (1)

offline reinforcement learning (2) recurrent neural network (2) model-based reinforcement learning (2) policy learning (1) off-policy learning (1) partial observability (1) learning rate (1) meta-reinforcement learning (1) recurrent reinforcement learning (1) dynamics model (1) environment adaptation (1) imperfect demonstration (1) context encoder (1) context sensitive policy (1) sudden change (1) out-of-support region (1) adaptable policy (1) reward consistency (1) transition filter (1) reweighting (1)