Jianzhun Shao

multi-agent reinforcement learning (4) offline reinforcement learning (3) partial observability (2) skill discovery (2) unsupervised reinforcement learning (2) centralized training decentralized execution (2) pose estimation (1) risk management (1) reinforcement learning (1) policy learning (1) deep learning (1) hierarchical reinforcement learning (1) markov decision process (1) mutual information (1) latent variable model (1) weakly supervised learning (1) mutual information maximization (1) attention mechanism (1) distribution shift (1) computer vision (1)