Adaptive rollout methods for group-relative reinforcement learning typically allocate a fixed per-update budget across prompts. We instead study how to coordinate a finite rollout budget over the entire training horizon. We formulate this problem using a concave surrogate utility of cumulative prompt exposure and intro...
Yi-Ming Zong, Yi-Ge Wang, Xin-Ting Hu et al.· 0 citations
Neural combinatorial optimization (NCO) relies on parallel solution sampling for training, yet existing methods fail to fully exploit the rich information latent in a co-sampled solution group. Preference-optimization methods anchor on the single best solution and discard fine-grained quality and structural signal from...
Yuan-Yu Li, Jin-Tao Xu, Zijiang Liu et al.· 0 citations
DualCert introduces constraint-coupled learning, in which current degree equations and dynamically separated subtour-elimination constraints (SECs) define each learned transition, and achieves a mean tour-cost gap of 0.0573%, smaller than the reported NeuroLKH mean gap.
Yancheng Song, Yong-Zhi Qi, Wei Qi et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.