搜索筛选:
搜索耗时4.9302秒,为你在为你在102,285,761篇论文里面共找到 1 篇相符的论文内容
发布年度:
Least-Squares Temporal Difference Learning with Eligibility Traces based on Regularized Extreme Lear
[会议论文] 作者：Dazi Li,Luntong Li,Tianheng Song,
来源：第26届中国过程控制会议 年份：2015
The task of learning the value function under a fixed policy in continuous Markov decision processes(MDPs)is considered.Although ELM based approximator can achieve better performance in learning predi...
相关搜索：
