1
Informed Asymmetric Actor-Critic: Leveraging Privileged Signals Beyond Full-State Access
ICML 2026 论文提出新型不对称演员-评论家框架,利用特权信号突破全局状态假设,大幅提升强化学习样本效率。
arXiv:2509.26000v3 Announce Type: replace Abstract: Asymmetric reinforcement learning leverages privileged information available during training to im…