Discrete Event Dynamic Systems. 2003;13(1-2):111-148. doi: 10.1023/a:1022145020786 Q31.02025

Approximate Gradient Methods in Policy-Space Optimization of Markov Reward Processes

马尔可夫奖励过程策略空间优化中的近似梯度方法

DOI: 10.1023/a:1022145020786

摘要 查看摘要

Copyright © Discrete Event Dynamic Systems. 中文内容为AI机器翻译，仅供参考！