General Self-Motivation and Strategy Identification: Case Studies Based on Sokoban and Pac-Man

In this paper, we use empowerment, a recently introduced biologically inspired measure, to allow an AI player to assign utility values to potential future states within a previously unencountered game without requiring explicit specification of goal states. We further introduce strategic affinity, a...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on computational intelligence and AI in games. Jg. 6; H. 1; S. 1 - 17
Hauptverfasser: Anthony, Tom, Polani, Daniel, Nehaniv, Chrystopher L.
Format: Journal Article
Sprache:Englisch
Veröffentlicht: IEEE 01.03.2014
Schlagworte:
Affinity
Artificial intelligence
Artificial intelligence (AI)
Cognition
Computers
Entropy
Games
information theory
Intelligence
Mutual information
Players
Random variables
Specifications
Strategy
Utilities
ISSN:1943-068X, 1943-0698
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:In this paper, we use empowerment, a recently introduced biologically inspired measure, to allow an AI player to assign utility values to potential future states within a previously unencountered game without requiring explicit specification of goal states. We further introduce strategic affinity, a method of grouping action sequences together to form "strategies," by examining the overlap in the sets of potential future states following each such action sequence. We also demonstrate an information-theoretic method of predicting future utility. Combining these methods, we extend empowerment to soft-horizon empowerment which enables the player to select a repertoire of action sequences that aim to maintain anticipated utility. We show how this method provides a proto-heuristic for nonterminal states prior to specifying concrete game goals, and propose it as a principled candidate model for "intuitive" strategy selection, in line with other recent work on "self-motivated agent behavior." We demonstrate that the technique, despite being generically defined independently of scenario, performs quite well in relatively disparate scenarios, such as a Sokoban-inspired box-pushing scenario and in a Pac-Man-inspired predator game, suggesting novel and principle-based candidate routes toward more general game-playing algorithms.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1943-068X
1943-0698
DOI:10.1109/TCIAIG.2013.2295372