1
Optimizing Regret
计量经济学前沿论文，探讨如何系统性地优化决策中的遗憾值问题。
arXiv:2607.18866v1 Announce Type: cross Abstract: Building on the identity that expected regret equals the covariance between costs and decisions, thi…
2
Inverting the Bellman Equation: From $Q$-Values to World Models
从Q值反向推导世界模型，逆Bellman方程新方法带来强化学习理论突破。
arXiv:2606.21173v1 Announce Type: cross Abstract: Model-based and model-free reinforcement learning are traditionally viewed as separate paradigms: in…