.png){kind=icon}
返回
Multiple Model Q-Learning for Stochastic Asynchronous Rewards
.png){kind=icon}
PRE
AI
DOI：10.1007/s10846-015-0222-2.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
This paper investigates reinforcement learning problems where a stochastic time delay is present in the reinforcement signal, but the delay is unknown to the learning agent. This work posits that the agent may receive individual reinforcements out of order, which is a relaxation of an important assumption in previous works from the literature. To that end, a stochastic time delay is introduced into a mobile robot line-following application. The main contribution of this work is to provide a novel stochastic approximation algorithm, which is an extension of Q-learning, for the time-delayed reinforcement problem. The paper includes a proof of convergence as well as grid world simulation results from MATLAB, results of line-following simulations within the Cyberbotics Webots mobile robot simulator, and finally, experimental results using an e-Puck mobile robot to follow a real track despite the presence of large, stochastic time delays in its reinforcement signal.
Keyword:
Reinforcement learning
Markov decision process
Stochastic time delay
Jitter
Delayed reinforcement
Multiple models
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
J
IF:
2.8
论文数:
3.9K
被引数:
6.9K
机构
引用论文
Defect-related photoluminescence properties of as-synthesized and annealed NiO nanostructures via hydrothermal method通过水热法合成和退火的NiO纳米结构的缺陷相关的光致发光特性
PREAI
分享收藏
Failure Prediction and Surface Characterization of GFRP Laminates: A Study of Stepwise Loading.png)
Polymers
OAAI
PolymersIF0
OAAI分享收藏
查看更多内容