零和部分可观测随机博弈新算法：保守策略迭代
Conservative Policy Iteration For Zero-Sum POSGs
博弈论方向的论文，讲怎么在部分可观测零和博弈里做策略迭代，跟 PBVI、HSVI、CFR+ 比了大 horizon 场景，做相关研究的可以看。
一篇 arXiv 论文提出面向有限时域零和部分可观测随机博弈（zs-POSGs）的近似策略迭代算法。方法为每个玩家维护一个策略，沿占用状态轨迹联合更新，每次更新只用当前联合策略诱导的单个支撑超平面，而非逼近完整中心值函数。算法交替执行局部策略改进、保守更新和持续探索，把计算集中在当前联合策略可被利用的占用区域。在有限时域零和 POSG 基准上，该方法在小 horizon 时与 PBVI、HSVI、CFR+ 相当，大 horizon 时通常在运行时间与可利用性权衡上更优。
Conservative Policy Iteration For Zero-Sum POSGs
Occupancy-state reductions make dynamic programming possible for zero-sum partially observable stochastic games (zs-POSGs). Existing point-based solvers usually optimise a central value function. This restores Bellman recursion, but it requires point-based updates over high-dimensional occupancy spaces. We introduce an approximate policy-iteration algorithm for finite-horizon zs-POSGs. The method maintains one policy per player and updates both jointly along occupancy trajectories induced by conservative policy updates. Instead of approximating a full central value function, each update uses a single supporting hyperplane induced by the current joint policy. The algorithm alternates local policy improvements, conservative updates, and persistent exploration. Computation is therefore concentrated on occupancy regions where the current joint policy is exploitable. On finite-horizon zero-sum POSG benchmarks, the method is competitive at small horizons and often improves the runtime-exploitability trade-off at larger horizons compared with PBVI, HSVI, and CFR+.