arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2012.01244cs.AIcs.NE
收藏

按访问国分列的代理人一般特征

General Characterization of Agents by States they Visit

University of Eastern Finland(东芬兰大学);National University of Singapore(新加坡国立大学)

Anssi Kanervisto, Tomi Kinnunen, Ville Hautamäki

摘要:

决策代理或其策略的行为特征(BC)用于研究训练算法的结果,并作为算法本身的一部分,以鼓励独特的策略,匹配专家策略或限制每次更新对策略的更改。然而,以前提出的解决方案是不适用的一般情况下,无论是由于缺乏表达能力,计算约束或政策或环境的约束。此外,许多巴塞尔公约依赖于政策的行动。我们讨论并演示了这些BC是如何误导的,特别是在随机环境中,并提出了一种新的解决方案,根据国家政策访问。我们运行实验来评估所提出的BC对基线的质量,并评估它们在学习训练算法,新颖性搜索和信任区域策略优化中的使用。该代码可在https://github.com/miffyli/policy-supervectors上获得。

英文摘要:

Behavioural characterizations (BCs) of decision-making agents, or their policies, are used to study outcomes of training algorithms and as part of the algorithms themselves to encourage unique policies, match expert policy or restrict changes to policy per update. However, previously presented solutions are not applicable in general, either due to lack of expressive power, computational constraint or constraints on the policy or environment. Furthermore, many BCs rely on the actions of policies. We discuss and demonstrate how these BCs can be misleading, especially in stochastic environments, and propose a novel solution based on what states policies visit. We run experiments to evaluate the quality of the proposed BC against baselines and evaluate their use in studying training algorithms, novelty search and trust-region policy optimization. The code is available at https://github.com/miffyli/policy-supervectors.

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。

↑