arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2602.03146cs.AI
收藏

通用智能体包含世界模型,即使在部分可观测性和随机性下

General Agents Contain World Models, even under Partial Observability and Stochasticity

Dovetail Research(Dovetail研究)

Santiago Cifuentes

AI总结:

本研究证明了即使在部分可观测性和随机性下,通用智能体仍需学习环境模型。

摘要:

决定智能体是否拥有对其周围世界的模型是理解其能力和限制的关键步骤。在[10]中,证明了在特定框架下,每个近优且通用的智能体都包含足够的环境知识,使其能够通过将智能体作为黑箱查询来近似重建环境。该结果依赖于假设智能体是确定性的,且环境是完全可观测的。在本工作中,我们通过将定理扩展到在部分可观测环境中运行的随机智能体,消除了这两个假设。从根本上说,这表明随机智能体无法通过随机化来避免学习其环境。我们还通过弱化通用性的概念,证明了更弱的智能体已经包含其操作世界的模型。

英文摘要:

Deciding whether an agent possesses a model of its surrounding world is a fundamental step toward understanding its capabilities and limitations. In [10], it was shown that, within a particular framework, every almost optimal and general agent necessarily contains sufficient knowledge of its environment to allow an approximate reconstruction of it by querying the agent as a black box. This result relied on the assumptions that the agent is deterministic and that the environment is fully observable. In this work, we remove both assumptions by extending the theorem to stochastic agents operating in partially observable environments. Fundamentally, this shows that stochastic agents cannot avoid learning their environment through the usage of randomization. We also strengthen the result by weakening the notion of generality, proving that less powerful agents already contain a model of the world in which they operate.

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。

↑