Language:

Anticipatory Classifier System with Average Reward Criterion in Discretized Multi-Step Environments

Applied sciences, 2021-01, Vol.11 (3), p.1098 [Peer Reviewed Journal]

Full text available

Citations Cited by

Title:
Anticipatory Classifier System with Average Reward Criterion in Discretized Multi-Step Environments
Author: Kozłowski, Norbert ; Unold, Olgierd
Subjects: Accuracy ; Algorithms ; anticipatory classifier systems ; Classifiers ; genetic algorithms ; Learning ; Learning algorithms ; learning classifier systems ; Neural networks ; OpenAI gym ; Optimization techniques ; Perceptions ; Reinforcement ; reinforcement learning
Is Part Of: Applied sciences, 2021-01, Vol.11 (3), p.1098
Description: Initially, Anticipatory Classifier Systems (ACS) were designed to address both single and multistep decision problems. In the latter case, the objective was to maximize the total discounted rewards, usually based on Q-learning algorithms. Studies on other Learning Classifier Systems (LCS) revealed many real-world sequential decision problems where the preferred objective is the maximization of the average of successive rewards. This paper proposes a relevant modification toward the learning component, allowing us to address such problems. The modified system is called AACS2 (Averaged ACS2) and is tested on three multistep benchmark problems.
Publisher: Basel: MDPI AG
Language: English
Identifier: ISSN: 2076-3417
EISSN: 2076-3417
DOI: 10.3390/app11031098
Source: ROAD: Directory of Open Access Scholarly Resources
ProQuest Central
DOAJ Directory of Open Access Journals

Back to results list


INSPIRE LIBRARY - TON DUC THANG UNIVERSITY	(84-028) 37 755 057	Feedback
19 Nguyen Huu Tho St. Dist.7, HCM	thuvien@tdtu.edu.vn	Feedback

Searching Remote Databases, Please Wait