Viewing classifier systems as model free learning in POMDPs

被引：0

作者：

Hayashi, A ^{[1
]}

Suematsu, N ^{[1
]}

机构：

[1] Hiroshima City Univ, Fac Informat Sci, Asaminami Ku, Hiroshima 7313194, Japan

来源：

ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 11 | 1999年 / 11卷

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

Classifier systems are now viewed disappointing because of their problems such as the rule strength vs rule set performance problem and the credit assignment problem. In order to solve the problems, we have developed a hybrid classifier system: GLS (Generalization Learning System). In designing GLS, we view CSs as model free learning in POMDPs and take a hybrid approach to finding the best generalization, given the total number of rules. GLS uses the policy improvement procedure by Jaakkola et al. for an locally optimal stochastic policy when a set of rule conditions is given. GLS uses GA to search for the best set of rule conditions.

引用

页码：989 / 995

页数：7

共 50 条

[31] A model-free Bayesian classifier
Geng, Zhiqiang
Meng, Qingchao
Bai, Ju
Chen, Jie
Han, Yongming
Wei, Qin
Ouyang, Zhi
INFORMATION SCIENCES, 2019, 482 : 171 - 188
[32] Evolution of control with learning classifier systems
Karlsen M.R.
Moschoyiannis S.
Applied Network Science, 3 (1)
[33] Learning Belief Representations for Imitation Learning in POMDPs
Gangwani, Tanmay
Lehman, Joel
Liu, Qiang
Peng, Jian
35TH UNCERTAINTY IN ARTIFICIAL INTELLIGENCE CONFERENCE (UAI 2019), 2020, 115 : 1061 - 1071
[34] A computational model for the Cognitive Immune System theory based on Learning Classifier Systems
Voigt, Daniel
Wirth, Henry
Dilger, Werner
ARTIFICIAL IMMUNE SYSTEMS, PROCEEDINGS, 2007, 4628 : 264 - +
[35] Learning classifier systems from a reinforcement learning perspective
P. L. Lanzi
Soft Computing, 2002, 6 (3) : 162 - 170
[36] Anticipatory Learning Classifier Systems and Factored Reinforcement Learning
Sigaud, Olivier
Butz, Martin V.
Kozlova, Olga
Meyer, Christophe
ANTICIPATORY BEHAVIOR IN ADAPTIVE LEARNING SYSTEMS: FROM PSYCHOLOGICAL THEORIES TO ARTIFICIAL COGNITIVE SYSTEMS, 2009, 5499 : 321 - +
[37] Learning Classifier Systems From Principles to Modern Systems
Stein, Anthony
PROCEEDINGS OF THE 2019 GENETIC AND EVOLUTIONARY COMPUTATION CONFERENCE COMPANION (GECCCO'19 COMPANION), 2019, : 747 - 769
[38] Mapping artificial immune systems into learning classifier systems
Vargas, PA
de Castro, LN
Von Zuben, FJ
LEARNING CLASSIFIER SYSTEMS, 2002, 2661 : 163 - 186
[39] A scalable model-free recurrent neural network framework for solving POMDPs
Liu, Zhenzhen
Elhanany, Itamar
2007 IEEE INTERNATIONAL SYMPOSIUM ON APPROXIMATE DYNAMIC PROGRAMMING AND REINFORCEMENT LEARNING, 2007, : 119 - +
[40] Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPs
Ni, Tianwei
Eysenbach, Benjamin
Salakhutdinov, Ruslan
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,

← 1 2 3 4 5 →