Multi-Step Alignment As Markov Games: an Optimistic Online Gradient Descent Approach with Convergence GuaranteesYongtao Wu,Luca Viano,Yihang Chen,Zhenyu Zhu,Kimon Antonakopoulos,Quanquan Gu,Volkan CevherCoRR（2025）引用 0|浏览3AI 理解论文溯源树样例生成溯源树，研究论文发展脉络Chat Paper正在生成论文摘要
