Hongchang Zhang

offline reinforcement learning (4) multi-agent reinforcement learning (3) skill discovery (2) partial observability (2) unsupervised reinforcement learning (2) extrapolation error (2) centralized training decentralized execution (2) importance sampling (1) policy improvement (1) hierarchical reinforcement learning (1) distribution shift (1) behavior policy (1) mutual information maximization (1) latent variable model (1) attention mechanism (1) zero-shot generalization (1) skill learning (1) policy iteration (1) unsupervised skill discovery (1) out-of-distribution detection (1)