Szczegóły publikacji
Opis bibliograficzny
Comparison of strategy learning methods in Farmer-Pest problem for various complexity environments without delays / Bartłomiej ŚNIEŻYŃSKI, Jacek DAJDA // Journal of Computational Science ; ISSN 1877-7503. — 2013 — vol. 4 iss. 3 spec. iss., s. 144–151. — Bibliogr. s. 150–151, Abstr. — ICCS 2011 workshop : agent-based simulation, adaptative algorithms : Singapore, June 1–3, 2011
Autorzy (2)
Słowa kluczowe
Dane bibliometryczne
| ID BaDAP | 74114 |
|---|---|
| Data dodania do BaDAP | 2013-06-18 |
| Tekst źródłowy | URL |
| DOI | 10.1016/j.jocs.2012.03.003 |
| Rok publikacji | 2013 |
| Typ publikacji | referat w czasopiśmie |
| Otwarty dostęp |  |
| Czasopismo/seria | Journal of Computational Science |
Abstract
In this paper effectiveness of several agent strategy learning algorithms is compared in a new multi-agent Farmer Pest learning environment. Learning is often utilized by multi-agent systems which can deal with complex problems by means of their decentralized approach. With a number of learning methods available, a need for their comparison arises. This is why we designed and implemented new multidimensional Farmer Pest problem domain, which is suitable for benchmarking learning algorithms. This paper presents comparison results for reinforcement learning (SARSA) and supervised learning (Naive Bayes, C4.5 and Ripper). These algorithms are tested on configurations with various complexity with not delayed rewards. The results show that algorithm performances depend highly on the environment configuration and various conditions favor different learning algorithms. (C) 2012 Elsevier B.V. All rights reserved.
