TD algorithm based on double-layer fuzzy partitioning

When dealing with the continuous space problems,the traditional Q-iteration algorithms based on lookup-table or function approximation converge slowly and are diff lt to get a continuous policy.To overcome the above weak-nesses,an on-policy TD algorithm named DFP-OPTD was proposed based on double-la...

Fuld beskrivelse

Bibliografiske detaljer

Principais autores:	Xiang MU, Quan LIU, Qi-ming FU, Hong-kun SUN, Xin ZHOU
Format:	Artigo
Sprog:	Chinês
Udgivet:	Editorial Department of Journal on Communications 2013-10-01
Serier:	Tongxin xuebao
Fag:	reinforcement learning;on-policy;gradient descent;;double layer fuzzy partitioning;continuous action policy
Online adgang:	http://www.joconline.com.cn/thesisDetails#10.3969/j.issn.1000-436x.2013.10.011
Tags:	Tilføj Tag Ingen Tags, Vær først til at tagge denne postø!