arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.11404cs.AI
收藏

POMDPs中的在线规划及其自改进仿真器

Online Planning in POMDPs with Self-Improving Simulators

Delft University of Technology(代尔夫特理工大学);Centrum Wiskunde & Informatica(荷兰国家数学与计算机科学研究所)

Jinke He, Miguel Suau, Hendrik Baier, Michael Kaisers, Frans A. Oliehoek

摘要:

当时间预算有限时,我们如何在大型复杂的环境中有效地进行计划?考虑到环境的原始模拟器,这可能是计算上非常苛刻,我们建议在线学习一个近似的,但更快的模拟器,随着时间的推移而改进。为了可靠和有效地计划,而近似模拟器正在学习,我们开发了一种方法,自适应地决定使用哪个模拟器为每个模拟,基于一个统计,测量近似模拟器的准确性。这允许我们使用近似模拟器来代替原始模拟器,以便在当前环境下足够准确时进行更快的模拟,从而权衡模拟速度和准确性。在两个大的领域的实验结果表明,当与POMCP集成,我们的方法允许计划随着时间的推移提高效率。

英文摘要:

How can we plan efficiently in a large and complex environment when the time budget is limited? Given the original simulator of the environment, which may be computationally very demanding, we propose to learn online an approximate but much faster simulator that improves over time. To plan reliably and efficiently while the approximate simulator is learning, we develop a method that adaptively decides which simulator to use for every simulation, based on a statistic that measures the accuracy of the approximate simulator. This allows us to use the approximate simulator to replace the original simulator for faster simulations when it is accurate enough under the current context, thus trading off simulation speed and accuracy. Experimental results in two large domains show that when integrated with POMCP, our approach allows to plan with improving efficiency over time.

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。

↑