.png){kind=icon}
返回
Feature-based methods for large scale dynamic programming
.png){kind=icon}
OA
AI
DOI：10.1007/BF00114724.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We develop a methodological framework and present a few different ways in which dynamic programming and compact representations can be combined to solve large scale stochastic control problems. In particular, we develop algorithms that employ two types of feature-based compact representations; that is, representations that involve feature extraction and a relatively simple approximation architecture. We prove the convergence of these algorithms and provide bounds on the approximation error. As an example, one of these algorithms is used to generate a strategy for the game of Tetris. Furthermore, we provide a counterexample illustrating the difficulties of integrating compact representations with dynamic programming, which exemplifies the shortcomings of certain simple approaches.
Keyword:
compact representation
curse of dimensionality
dynamic programming
features
function approximation
neuro-dynamic programming
reinforcement learning
期刊
IF:
2.9
论文数:
2.7K
被引数:
3.4W
机构
暂无机构信息
引用论文
.png){kind=icon}
An Integrated Scheduling and Retransmission Proposal for Firm Real-Time Traffic in IEEE 802.11e
PREAI
分享收藏 没有更多内容
没有更多内容