Haobin Jiang

Artificial Intelligence (4) Core AI (4) Reinforcement Learning (2) Methods (2) Machine Learning (1) Robotics (1) Learning Paradigms (1) Learning Types (1) Systems (1)

multi-agent reinforcement learning (1) hierarchical planning (1) flow matching (1) compositional generalization (1) mutual information (1) model-based reinforcement learning (1) recursive reasoning (1) end-to-end learning (1) skill learning (1) policy adaptation (1) sparse reward (1) intrinsic reward (1) opponent modeling (1) semantic abstraction (1) latent plan (1) coordinated exploration (1) language instruction (1) environment model (1) multi-agent system (1) novelty sharing (1)