1
How to sketch a learning algorithm
手把手教你从零构思学习算法，把抽象设计思路拆解成可操作的步骤，适合想深入算法原理的读者。
arXiv:2604.07328v3 Announce Type: replace Abstract: How does the choice of training data influence an AI model? This broad question is of central impo…
2
Learning to Decide with AI Assistance under Human-Alignment
前沿研究探讨如何让AI助手在符合人类偏好的前提下辅助决策，揭秘人机对齐新方法
arXiv:2605.12646v2 Announce Type: replace-cross Abstract: It is widely agreed that when AI models assist decision-makers in high-stakes domains by pre…
3
One-Step Bellman Alignment Enables Provably Efficient Transfer in Online RL
提出一步贝尔曼对齐方法，理论上证明能实现高效的在线强化学习迁移。
arXiv:2601.21924v2 Announce Type: replace Abstract: We study online transfer reinforcement learning (RL) in episodic Markov decision processes, where …
4
Target-Aligned Bellman Backup for Cross-domain Offline Reinforcement Learning
跨领域离线强化学习新方法，用对齐贝尔曼备份解决域间转移难题。
arXiv:2605.22376v1 Announce Type: new Abstract: Cross-domain offline reinforcement learning (CDRL) aims to improve policy learning in a target domain …
5
Gradient Iterated Temporal-Difference Learning
强化学习新突破：梯度迭代TD学习算法，解决半梯度更新缺陷，提升长期决策稳定性
arXiv:2603.07833v2 Announce Type: replace-cross Abstract: Temporal-difference (TD) learning is highly effective at controlling and evaluating an agent…