Heuristic Q-learning soccer players: a new reinforcement learning approach to RoboCup simulation

Authors:
Luiz A. Celiberto, Jr.;Jackson Matsuura;Reinaldo A. C. Bianchi
Affiliations:
Centro Universitário da FEI, São Bernardo do Campo, SP, Brazil and Instituto Tecnológico de Aeronáutica, São José dos Campos, SP, Brazil;Instituto Tecnológico de Aeronáutica, São José dos Campos, SP, Brazil;Centro Universitário da FEI, São Bernardo do Campo, SP, Brazil
Venue:
EPIA'07 Proceedings of the aritficial intelligence 13th Portuguese conference on Progress in artificial intelligence
Year:
2007

Citing 5
Cited 0

Artificial intelligence: a modern approach

Artificial intelligence: a modern approach
The effect of representation and knowledge on goal-directed exploration with reinforcement-learning algorithms

Machine Learning - Special issue on reinforcement learning
Machine Learning

Machine Learning
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
Generalized Markov Decision Processes: Dynamic-programming and Reinforcement-learning Algorithms

Generalized Markov Decision Processes: Dynamic-programming and Reinforcement-learning Algorithms

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper describes the design and implementation of a 4 player RoboCup Simulation 2D team, which was build by adding Heuristic Accelerated Reinforcement Learning capabilities to basic players of the well-known UvA Trilearn team. The implemented agents learn by using a recently proposed Heuristic Reinforcement Learning algorithm, the Heuristically Accelerated Q-Learning (HAQL), which allows the use of heuristics to speed up the well-known Reinforcement Learning algorithm Q-Learning. A set of empirical evaluations was conducted in the RoboCup 2D Simulator, and experimental results obtained while playing with other teams shows that the approach adopted here is very promising.