1
Offline RL with Hierarchical Action Chunking
提出分层动作分块机制，让离线RL能够高效学习长程动作序列，显著提升复杂任务成功率。
arXiv:2607.20834v1 Announce Type: new Abstract: Offline goal-conditioned reinforcement learning (RL) holds the promise of learning general-purpose pol…