当前位置: X-MOL 学术arXiv.cs.SY › 论文详情
Safe Reinforcement Learning via Projection on a Safe Set: How to Achieve Optimality?
arXiv - CS - Systems and Control Pub Date : 2020-04-02 , DOI: arxiv-2004.00915
Sebastien Gros; Mario Zanon; Alberto Bemporad

For all its successes, Reinforcement Learning (RL) still struggles to deliver formal guarantees on the closed-loop behavior of the learned policy. Among other things, guaranteeing the safety of RL with respect to safety-critical systems is a very active research topic. Some recent contributions propose to rely on projections of the inputs delivered by the learned policy into a safe set, ensuring that the system safety is never jeopardized. Unfortunately, it is unclear whether this operation can be performed without disrupting the learning process. This paper addresses this issue. The problem is analysed in the context of $Q$-learning and policy gradient techniques. We show that the projection approach is generally disruptive in the context of $Q$-learning though a simple alternative solves the issue, while simple corrections can be used in the context of policy gradient methods in order to ensure that the policy gradients are unbiased. The proposed results extend to safe projections based on robust MPC techniques.
更新日期:2020-04-03

 

全部期刊列表>>
智控未来
聚焦商业经济政治法律
跟Nature、Science文章学绘图
控制与机器人
招募海内外科研人才,上自然官网
隐藏1h前已浏览文章
课题组网站
新版X-MOL期刊搜索和高级搜索功能介绍
ACS材料视界
x-mol收录
湖南大学化学化工学院刘松
上海有机所
李旸
南方科技大学
西湖大学
X-MOL
支志明
中山大学化学工程与技术学院
试剂库存
天合科研
down
wechat
bug