近似确定世界中Markov模型的决策Agent搜索
Decision Making Agent Searching for Markov Models in Near-Deterministic World
摘要：
强化学习具有坚实的基础，但在部分观察（非马尔可夫）环境中变得低效。因此，一个学习代理--天生就有一个表示和一个策略--可能希望研究马尔可夫性质在多大程度上成立。我们提出了一个学习架构，利用组合策略优化来克服非马尔可夫性，并开发有效的行为，这是很容易继承的，测试的行为状态的马尔可夫属性，并纠正非马尔可夫性通过运行一个确定性因子有限状态模型，它可以学习。我们说明了近确定性的女士吃豆人游戏中的架构的属性。我们从进化、个体和社会学习的角度分析了这种体系结构。
英文摘要：
Reinforcement learning has solid foundations, but becomes inefficient in partially observed (non-Markovian) environments. Thus, a learning agent -born with a representation and a policy- might wish to investigate to what extent the Markov property holds. We propose a learning architecture that utilizes combinatorial policy optimization to overcome non-Markovity and to develop efficient behaviors, which are easy to inherit, tests the Markov property of the behavioral states, and corrects against non-Markovity by running a deterministic factored Finite State Model, which can be learned. We illustrate the properties of architecture in the near deterministic Ms. Pac-Man game. We analyze the architecture from the point of view of evolutionary, individual, and social learning.
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。
