arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2106.09161cs.LGcs.LOcs.SYeess.SY
收藏

Mungojerrie:线性时间目标的强化学习

Mungojerrie: Reinforcement Learning of Linear-Time Objectives

University of Twente(特文特大学);University of Colorado Boulder(科罗拉多大学博尔德分校);University of Liverpool(利物浦大学)

Ernst Moritz Hahn, Mateo Perez, Sven Schewe, Fabio Somenzi, Ashutosh Trivedi, Dominik Wojtczak

摘要:

强化学习在没有系统先验知识的情况下综合控制器。在每一个时间步,都有一个奖励。控制器优化这些奖励的折扣和。应用这类算法需要设计奖励方案,这通常是手动完成的。设计师必须确保他们的意图被准确捕捉。这可能不是微不足道的,并且容易出错。这种手动编程的替代方案类似于直接在汇编中编程,是用形式语言指定目标并将其“编译”为奖励方案。Mungojerrie(https://plv.colorado.edu/mungojerrie/)是一个用于测试$ω$ -有限模型上的常规目标的奖励方案的工具。该工具包含强化学习算法和概率模型检查器。Mungojerrie支持PRISM中指定的模型和HOA中指定的$ω$ -自动机。

英文摘要:

Reinforcement learning synthesizes controllers without prior knowledge of the system. At each timestep, a reward is given. The controllers optimize the discounted sum of these rewards. Applying this class of algorithms requires designing a reward scheme, which is typically done manually. The designer must ensure that their intent is accurately captured. This may not be trivial, and is prone to error. An alternative to this manual programming, akin to programming directly in assembly, is to specify the objective in a formal language and have it "compiled" to a reward scheme. Mungojerrie (https://plv.colorado.edu/mungojerrie/) is a tool for testing reward schemes for $ω$-regular objectives on finite models. The tool contains reinforcement learning algorithms and a probabilistic model checker. Mungojerrie supports models specified in PRISM and $ω$-automata specified in HOA.

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。

↑