2 papers
cs.AI2026
Phase-Aware Guidance Injection for Recurrent MAPPO in Assembly-Line Disruption Recovery
Xin Huang, Yongcai Wang, Fengyi Zhang +3
Disruption recovery in industrial assembly lines requires timely decisions under machine faults, worker absence, and emergency orders. Existing methods either rely on rigid handcra…
cs.LG2025
Feasibility-Aware Pessimistic Estimation: Toward Long-Horizon Safety in Offline RL
Zhikun Tao
Offline safe reinforcement learning(OSRL) derives constraint-satisfying policies from pre-collected datasets, offers a promising avenue for deploying RL in safety-critical real-wor…