13 upvotes · 17 JUL 2026 · Kai Ruan, Jinghao Lin, Zihe Huang et al.
This paper investigates the use of the Muon optimizer in reinforcement learning (RL) post-training and finds that it can significantly improve the success rate of RL agents, especially when combined with other techniques like policy optimization and advantage estimation. Practitioners in RL may care about this research to explore new ways to improve the performance of their agents.
10 upvotes · 16 JUL 2026 · Weiwen Xu, Jia Liu, Hou Pong Chan et al.
This paper proposes a new method for advantage shaping in reinforcement learning called Contrastive Policy Optimization (CPO), which uses contrastive disagreement between reference-guided and vanilla generation distributions to indicate correctness. Practitioners might care because it can improve the effectiveness of reinforcement learning methods in generating correct responses.