Playing a Strategy Game with Knowledge-Based Reinforcement Learning

This paper presents knowledge-based reinforcement learning (KB-RL) as a method that combines a knowledge-based approach and a reinforcement learning (RL) technique into one method for intelligent problem solving. The proposed approach focuses on multi-expert knowledge acquisition, with the RL being...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:SN computer science Jg. 1; H. 2; S. 78
Hauptverfasser: Voss, Viktor, Nechepurenko, Liudmyla, Schaefer, Rudi, Bauer, Steffen
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Singapore Springer Singapore 01.03.2020
Springer Nature B.V
Schlagworte:
Algorithms
Artificial intelligence
Automation
Computer Imaging
Computer Science
Computer Systems Organization and Communication Networks
Data Structures and Information Theory
Deep learning
Games
Information Systems and Communication Service
Knowledge acquisition
Knowledge bases (artificial intelligence)
Knowledge representation
Machine learning
Neural networks
Ontology
Original Research
Pattern Recognition and Graphics
Problem solving
Semantics
Software
Software Engineering/Programming and Operating Systems
Strategy
Vision
Knowledge-based systems
Multi-expert knowledge base
Conflict resolution
Reinforcement learning
ISSN:2662-995X, 2661-8907
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:This paper presents knowledge-based reinforcement learning (KB-RL) as a method that combines a knowledge-based approach and a reinforcement learning (RL) technique into one method for intelligent problem solving. The proposed approach focuses on multi-expert knowledge acquisition, with the RL being applied as a conflict resolution strategy aimed at integrating the knowledge of multiple exerts into one knowledge base. The article describes the KB-RL approach in detail and applies the reported method to one of the most challenging problems of current artificial intelligence research, namely playing a strategy game. The results show that the KB-RL system is able to play and complete the full FreeCiv game, and to win against the computer players in various game settings. Moreover, with more games played, the system improves the gameplay by shortening the number of rounds that it takes to win the game. Overall, the reported experiment supports the idea that, based on human knowledge and empowered by RL, the KB-RL system can deliver a strong solution to the complex, multi-strategic problems, and, mainly, improve the solution with increased experience.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2662-995X
2661-8907
DOI:10.1007/s42979-020-0087-8