Learning System Using Hierarchical Fuzzy ART for Two-Player Games

The adaptive resonance theory (ART) can generate and grow the recognition categories based on the similarity between inputs and memories. This paper proposes a new learning system using hierarchical fuzzy ART for two-player games. The proposed system segments an input state space into subspaces by t...

Full description

Saved in:
Bibliographic Details
Main Authors: Kushida, J.-I., Nakaoka, I., Oba, K., Kamei, K.
Format: Conference Proceeding
Language:English
Subjects:
Control systems
Educational institutions
Fuzzy control
Fuzzy systems
Game theory
Information science
Learning systems
Resonance
State-space methods
Subspace constraints
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:The adaptive resonance theory (ART) can generate and grow the recognition categories based on the similarity between inputs and memories. This paper proposes a new learning system using hierarchical fuzzy ART for two-player games. The proposed system segments an input state space into subspaces by the fuzzy ARTs added hierarchically in proportion as the learning progress of players, and then learns pairs of input states and actions by the reinforcement learning. As the results of experiments, it is shown through a fighting simulation game that the player can acquire proper pairs of the input states and actions against the opponent player by learning using the proposed system.
DOI:10.1109/ICICIC.2009.253