基于概率自动机的操作条件反射计算模型  

Compute Model of Operant Conditioning Based on Probabilistic Automata

作　　者：阮晓钢[1] 蔡建羡[1,2] 戴丽珍[1] 

机构地区：[1]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 [2]防灾科技学院,河北三河065201

出　　处：《北京工业大学学报》2010年第8期1025-1030,共6页Journal of Beijing University of Technology

基　　金：国家自然科学基金资助项目(60774077);国家'八六三'计划资助项目(2007AA04Z226);北京市教委重点资助项目(KZ200810005002)

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.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 established to be applied to skinner-pigeon experiment of the peck button task. The pigeon learns this task in stages. In simulation,the model also acquires the task in a similar manner. The stochastic learning automaton has outstanding superiority in dealing with the problem of lack of prior knowledge,which lays a theoretical foundation for copying the behaviors of people and animal by robot learning.

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 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]