| 基于概率自动机的操作条件反射计算模型 |
| |
| 引用本文： | 阮晓钢,蔡建羡,戴丽珍.基于概率自动机的操作条件反射计算模型[J].北京工业大学学报,2010,36(8). |
| |
| 作者姓名： | 阮晓钢 蔡建羡 戴丽珍 |
| |
| 作者单位： | 北京工业大学,电子信息与控制工程学院,人工智能与机器人研究所,北京,100124;北京工业大学,电子信息与控制工程学院,人工智能与机器人研究所,北京,100124;防灾科技学院,河北三河,065201 |
| |
| 基金项目： | 国家自然科学基金资助项目，国家"八六三"计划资助项目，北京市教委重点资助项目 |
| |
| 摘 要： | 基于概率自动机构造了反应操作条件反射行为的随机学习自动机,以模拟斯金纳(Skinner)鸽子试验.该随机学习自动机是一种能在未知的随机环境中完成自适应决策的智能单元,它与随机环境构成闭环,能在与环境的交互过程中学习选取给予奖赏的最佳动作.试验结果表明:该自动机模型体现了动物的操作条件反射行为,具有和实际类似的学习效果,对于处理先验知识缺乏或不完备的问题具有优越性.
|
| 关 键 词： | 概率自动机 操作条件反射 随机学习自动机 Skinner鸽子试验 评价机制 学习机制 |
Compute Model of Operant Conditioning Based on Probabilistic Automata |
| |
| RUAN Xiao-gang,CAI Jian-xian,DAI Li-zhen.Compute Model of Operant Conditioning Based on Probabilistic Automata[J].Journal of Beijing Polytechnic University,2010,36(8). |
| |
| Authors: | RUAN Xiao-gang CAI Jian-xian DAI Li-zhen |
| |
| Affiliation: | RUAN Xiao-gang1,CAI Jian-xian1,2,DAI Li-zhen1(1. Institute of Artificial Intelligence and Robotics,Electronic Information and Control Engineering,Beijing University of Technology,Beijing 100124,China,2. Institute of Disaster Prevention,Sanhe 065201,Hebei,China) |
| |
| Abstract: | This paper constructs a stochastic learning automaton that can respond the operant conditioning behavior based on probabilistic automata,which is used for simulating skinner-pigeon experiment. The stochastic learning automaton is a kind of intelligent unit which can accomplish adaptive decision under unknown environment,and so it can let an agent to adapt its actions to gain maximally from the environment while only being rewarded for correct performance. A stochastic learning automation model is establishe... |
| |
| Keywords: | probabilistic automata operant conditioning stochastic learning automaton skinner-pigeon experiment evaluation mechanism learning mechanism |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
