← 研踪 PaperTrailarXiv:2602.07473 · v3
Approximating the Reachability Value of Posterior-Deterministic POMDPs
首次提交 2026-02-07 18:09
版本更新 2026-11-06 22:35
雷达观测 2026-11-09 13:22
摘要
We introduce posterior-deterministic POMDPs, and we show that for this class of POMDPs, the maximal probability of reaching a given set of states can be approximated up to arbitrary precision. A POMDP is posterior-deterministic if the next state can be uniquely determined by the current state, the action taken, and the observation received. In particular, once the current state is known, it remains known forever. The class contains, for instance, multiple-environment MDPs equipped with a prior distribution over the environments, quasi-deterministic POMDPs, and the episodic version of the classical Tiger POMDP (Kaelbling et al. 1998).
观测到的版本
相邻记录可能跳过中间版本；首次发现 v2 及以上也会标为版本更新。
v3 · 2026-11-06 22:35 · 最新观测版本
Approximating the Reachability Value of Posterior-Deterministic POMDPs
We introduce posterior-deterministic POMDPs, and we show that for this class of POMDPs, the maximal probability of reaching a given set of states can be approximated up to arbitrary precision. A POMDP is posterior-deterministic if the next state can be uniquely determined by the current state, the action taken, and the observation received. In particular, once the current state is known, it remains known forever. The class contains, for instance, multiple-environment MDPs equipped with a prior distribution over the environments, quasi-deterministic POMDPs, and the episodic version of the classical Tiger POMDP (Kaelbling et al. 1998).
查看此版本解读 →查看此版本原文 ↗