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 2103.14600cs.ROcs.FLcs.LGcs.LO
收藏

无模型学习安全且有效的控制器

Model-Free Learning of Safe yet Effective Controllers

Duke University(杜克大学)

Alper Kamil Bozkurt, Yu Wang, Miroslav Pajic

AI总结:

本文研究学习安全且有效的控制策略,通过强化学习算法优先保证安全,再满足LTL规范,最后优化控制性能奖励。

摘要:

我们研究学习安全控制策略的问题,即最大化满足线性时序逻辑(LTL)任务规范的概率,以及捕获经典控制性能的折扣奖励。我们考虑未知环境建模为马尔可夫决策过程。我们提出一种无模型强化学习算法,学习一种策略,首先最大化确保安全的概率,然后是满足给定LTL规范的概率,最后是折扣后的控制质量奖励之和。最后,我们展示了基于强化学习的方法的应用性。

英文摘要:

We study the problem of learning safe control policies that are also effective; i.e., maximizing the probability of satisfying a linear temporal logic (LTL) specification of a task, and the discounted reward capturing the (classic) control performance. We consider unknown environments modeled as Markov decision processes. We propose a model-free reinforcement learning algorithm that learns a policy that first maximizes the probability of ensuring safety, then the probability of satisfying the given LTL specification and lastly, the sum of discounted Quality of Control rewards. Finally, we illustrate applicability of our RL-based approach.

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。

↑