.png){kind=icon}
返回
(Approximate) iterated successive approximations algorithm for sequential decision processes
.png){kind=icon}
PRE
AI
DOI：10.1007/s10479-012-1073-x.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The paper proves the convergence of (Approximate) Iterated Successive Approximations Algorithm for solving infinite-horizon sequential decision processes satisfying the monotone contraction assumption. At every stage of this algorithm, the value function at hand is used as a terminal reward to determine an (approximately) optimal policy for the one-period problem. This policy is then iterated for a (finite or infinite) number of times and the resulting return function is used as the starting value function for the next stage of the scheme. This method generalizes the standard successive approximations, policy iteration and Denardo's generalization of the latter.
Keyword:
Sequential decision processes
Markov decision chains
Successive approximations
Modified policy iteration
期刊
IF:
4.5
论文数:
8.0K
被引数:
2.1W
机构
引用论文
Critical Evaluation and Thermodynamic Optimization of the Li2O-Al2O3 and Li2O-MgO-Al2O3 Systems
PREAI
分享收藏Chinese fathers of children with intellectual disabilities: their perceptions of the child, family functioning, and their own needs for emotional support中国智力障碍儿童的父亲：他们对孩子、家庭功能以及自身情感支持需求的看法
OAAI
OAAI分享收藏A Novel Feature Identification Method of Pipeline In-Line Inspected Bending Strain Based on Optimized Deep Belief Network Model.png)
Energies
OAAI
EnergiesIF0
OAAI分享收藏分享收藏
查看更多内容