1
Robust Instruction Compliance in Cooperative Multi-Agent Reinforcement Learning
合作多智能体强化学习中，新方法应对指令干扰，显著提升鲁棒性与任务成功率。
arXiv:2605.12655v2 Announce Type: replace Abstract: Multi-agent reinforcement learning (MARL) in real-world use cases may need to adapt to external na…