| 一种自信学习自动机 |
| |
| 引用本文： | 刘晓.一种自信学习自动机[J].航空计算技术,1998,28(1):13-15. |
| |
| 作者姓名： | 刘晓 |
| |
| 作者单位： | 中国航空计算技术研究所!西安，710068 |
| |
| 摘 要： | 提出一种二次不动—惩罚变结构随机自动机模型（Q(IP)）。较之于其线性形式（L(IP)），新模型的学习带有一定的自信（当然，有时也可能是自负）。特别，跟传统自动机不同的是，新算法的极限行为同时兼具吸收壁和遍历性。
|
| 关 键 词： | 学习自动机 变结构随机自动机 强化学习 |
A Self-Confident Learning Automaton |
| |
| Liu Xiao.A Self-Confident Learning Automaton[J].Aeronautical Computer Technique,1998,28(1):13-15. |
| |
| Authors: | Liu Xiao |
| |
| Abstract: | In this paper, a model of the quadratic inaction-penalty variable structure stochastic automata, QIP, is presented. Compared with its linear counterpart (Lin),learning of the quadratic automaton is self-confident (and may also be, of cause, self-opinionated in some extremely bad cases). Especially, as opposed to the traditional automata, the limiting behavior of the proposed algorithm possesses both absorbing barriers and ergodicity. |
| |
| Keywords: | Learning automata Variable structure stochastic automata Reinforcement learning |
| 本文献已被 CNKI 维普 等数据库收录！ |
|
