GP-Gammon: using genetic programming to evolve backgammon players

Authors:
Yaniv Azaria;Moshe Sipper
Affiliations:
Department of Computer Science, Ben-Gurion University, Israel;Department of Computer Science, Ben-Gurion University, Israel
Venue:
EuroGP'05 Proceedings of the 8th European conference on Genetic Programming
Year:
2005

Citing 9
Cited 5

Genetic programming: on the programming of computers by means of natural selection

Genetic programming: on the programming of computers by means of natural selection
Genetic programming II: automatic discovery of reusable programs

Genetic programming II: automatic discovery of reusable programs
Temporal difference learning and TD-Gammon

Communications of the ACM
A success story or an old wives' tale? On judging experiments in evolutionary computation

Complexity
Genetic Programming III: Darwinian Invention & Problem Solving

Genetic Programming III: Darwinian Invention & Problem Solving
Achieving Efficient and Cognitively Plausible Learning in Backgammon

ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
Genetic Programming IV: Routine Human-Competitive Machine Intelligence

Genetic Programming IV: Routine Human-Competitive Machine Intelligence
Integrating Reinforcement Learning, Bidding and Genetic Algorithms

IAT '03 Proceedings of the IEEE/WIC International Conference on Intelligent Agent Technology
Strongly typed genetic programming

Evolutionary Computation

Human-competitive results produced by genetic programming

Genetic Programming and Evolvable Machines
A new software application for backgammon based on a heuristic algorithm

ECC'11 Proceedings of the 5th European conference on European computing conference
Fuzzeval: a fuzzy controller-based approach in adaptive learning for backgammon game

MICAI'05 Proceedings of the 4th Mexican international conference on Advances in Artificial Intelligence
Evolving third-person shooter enemies to optimize player satisfaction in real-time

EvoApplications'12 Proceedings of the 2012t European conference on Applications of Evolutionary Computation
Generating artificial neural networks for value function approximation in a domain requiring a shifting strategy

EvoApplications'13 Proceedings of the 16th European conference on Applications of Evolutionary Computation

Quantified Score

Hi-index	0.00

Visualization

Abstract

We apply genetic programming to the evolution of strategies for playing the game of backgammon. Pitted in a 1000-game tournament against a standard benchmark player—Pubeval—our best evolved program wins 58% of the games, the highest verifiable result to date. Moreover, several other evolved programs attain win percentages not far behind the champion, evidencing the repeatability of our approach.