强化学习理论新突破：线性Bellman完备MDP在确定性转移下实现端到端高效求解，值得算法研究者细读。
arXiv:2603.23461v2 Announce Type: replace Abstract: We study reinforcement learning (RL) with linear function approximation in Markov Decision Process…
用L-infinity Bellman算子解决CVaR马尔可夫决策过程奖励稀疏问题，理论创新扎实。
arXiv:2602.03778v2 Announce Type: replace-cross Abstract: Tail-end risk measures such as static conditional value-at-risk (CVaR) are used in safety-cr…
详解大模型强化学习全流程，从MDP构建到探索学习的模块化指南，前沿且系统。
arXiv:2606.21943v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become central to LLM post-training, yet the methods that dominate c…
从视觉演示中自动学习符号化POMDP，让机器人在不确定性下也能智能规划，论文提出PO-PDDL方法。
arXiv:2606.15654v1 Announce Type: cross Abstract: Real-world robot task planning must operate under both stochastic action execution and partial obser…
Q-learning新理论突破，细粒度依赖遗憾界优化算法性能。
arXiv:2510.06647v2 Announce Type: replace-cross Abstract: We study fine-grained gap-dependent regret bounds for model-free reinforcement learning in e…
强化学习新范式：动作触发部分可观测的MDP，理论推导贝尔曼方程
arXiv:2510.02149v2 Announce Type: replace Abstract: We introduce Action-Triggered Sporadically Traceable Markov Decision Processes (ATST-MDPs), a rein…
将采样与模型检查结合，为POMDP策略综合提供形式化保证，突破安全关键应用瓶颈。
arXiv:2605.14440v1 Announce Type: new Abstract: Partially Observable Markov Decision Processes (POMDPs) are the standard framework for decision-making…
逆向强化学习新突破：MLE与Min-Max-IRL等价性及快速统计率证明，线性奖励MDP下理论简洁有力。
arXiv:2605.14599v1 Announce Type: cross Abstract: We establish novel structural and statistical results for entropy-regularized min-max inverse reinfo…
提出General Dijkstra Search与动态潜路由后训练方法，实现MDP子策略最优时序组合，为语言模型强化学习提供新范式。
arXiv:2605.14323v1 Announce Type: cross Abstract: We investigate the temporal concatenation of sub-policies in Markov Decision Processes (MDP) with ti…