有界交互的Myhill-Nerode定理:通过智能体有界不可区分性获得规范抽象
The Myhill-Nerode Theorem for Bounded Interaction: Canonical Abstractions via Agent-Bounded Indistinguishability
AI总结:
本文研究了有限POMDP中有界交互的规范抽象,通过智能体有界不可区分性定义了规范商,并验证了其在时钟感知探针下的决策充分性及在潜在状态奖励下的近似界限。
摘要:
任何具有容量限制的观察者都会在其环境中诱导一个规范商:两个情况如果无法被有界智能体区分,则对智能体而言是相同的。本文针对有限POMDP进行了形式化。一个固定的有限状态控制器家族诱导了一个闭环Wasserstein伪度量,在观察历史上以及一个控制器家族无法区分的历史上合并。该商是规范的、最小的且唯一的——有界交互的Myhill-Nerode定理的类比。对于时钟感知探针,它在仅依赖智能体观察和行动的目标中是精确决策充分的;对于潜在状态奖励,我们使用观察Lipschitz近似界限。主要定理对象是时钟感知商;可扩展的确定性平稳实验研究了可处理的粗化,通过在小精确案例上测量间隙并在更大规模上经验性探索。我们在Tiger和GridWorld上验证了定理层面的声明。我们还报告了Tiger、GridWorld和RockSample上的操作案例研究,作为近似行为和运行时间的探索性诊断,而不是在没有可用的跨家族证书时的定理面向证据;更严格的压力测试已存档在附录和存档包中。
英文摘要:
Any capacity-limited observer induces a canonical quotient on its environment: two situations that no bounded agent can distinguish are, for that agent, the same. We formalise this for finite POMDPs. A fixed probe family of finite-state controllers induces a closed-loop Wasserstein pseudometric on observation histories and a probe-exact quotient merging histories that no controller in the family can distinguish. The quotient is canonical, minimal, and unique-a bounded-interaction analogue of the Myhill-Nerode theorem. For clock-aware probes, it is exactly decision-sufficient for objectives that depend only on the agent's observations and actions; for latent-state rewards, we use an observation-Lipschitz approximation bound. The main theorem object is the clock-aware quotient; scalable deterministic-stationary experiments study a tractable coarsening with gap measured on small exact cases and explored empirically at larger scale. We validate theorem-level claims on Tiger and GridWorld. We also report operational case studies on Tiger, GridWorld, and RockSample as exploratory diagnostics of approximation behavior and runtime, not as theorem-facing evidence when no exact cross-family certificate is available; heavier stress tests are archived in the appendix and artifact package.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。