Winning Ant Wars: Evolving a Human-Competitive Game Strategy Using Fitnessless Selection

Jaśkowski, Wojciech; Krawiec, Krzysztof; Wieloch, Bartosz

doi:10.1007/978-3-540-78671-9_2

Cited by 12 publications

(11 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Various forms of CEL have been successfully applied to many two-person games, including Backgammon [10], Chess [11], Checkers [12], NERO [13], Blackjack [14], Pong [15], AntWars [16], [17] and a small version of Go [18].…”

Section: A Coevolutionary Learningmentioning

confidence: 99%

Coevolutionary Temporal Difference Learning for Othello

Szubert

Jaśkowski

Krawiec

2009

2009 IEEE Symposium on Computational Intelligence and Games

Self Cite

View full text Add to dashboard Cite

This paper presents Coevolutionary Temporal Difference Learning (CTDL), a novel way of hybridizing coevolutionary search with reinforcement learning that works by interlacing one-population competitive coevolution with temporal difference learning. The coevolutionary part of the algorithm provides for exploration of the solution space, while the temporal difference learning performs its exploitation by local search. We apply CTDL to the board game of Othello, using weighted piece counter for representing players' strategies. The results of an extensive computational experiment demonstrate CTDL's superiority when compared to coevolution and reinforcement learning alone, particularly when coevolution maintains an archive to provide historical progress. The paper investigates the role of the relative intensity of coevolutionary search and temporal difference search, which turns out to be an essential parameter. The formulation of CTDL leads also to the introduction of Lamarckian form of coevolution, which we discuss in detail.

show abstract

Section: A Coevolutionary Learningmentioning

confidence: 99%

Coevolutionary Temporal Difference Learning for Othello

Szubert

Jaśkowski

Krawiec

2009

2009 IEEE Symposium on Computational Intelligence and Games

Self Cite

View full text Add to dashboard Cite

show abstract

“…Despite this simplicity, it produces effective solutions and is immune to noise to an extent that is comparable to kRO (assuming the optimal value of the k parameter for kRO is known in advance). In a separate study [5], we demonstrated its ability to evolve human-competitive players in a complex game with partially observable states. The downside of the method is the extra effort required to appoint the best-of-run individual.…”

Section: Discussionmentioning

confidence: 97%

Fitnessless coevolution

Jaśkowski

Krawiec

Wieloch

2008

Proceedings of the 10th Annual Conference on Genetic and Evolutionary Computation

Self Cite

View full text Add to dashboard Cite

We introduce fitnessless coevolution (FC), a novel method of comparative one-population coevolution. FC plays games between individuals to settle tournaments in the selection phase and skips the typical phase of evaluation. The selection operator applies a single-elimination tournament to a randomly drawn group of individuals, and the winner of the final round becomes the result of selection. Therefore, FC does not involve explicit fitness measure. We prove that, under a condition of transitivity of the payoff matrix, the dynamics of FC is identical to that of the traditional evolutionary algorithm. The experimental results, obtained on a diversified group of problems, demonstrate that FC is able to produce solutions that are equally good or better than solutions obtained using fitness-based one-population coevolution with different selection methods.

show abstract

“…At present, archiving techniques are used to provide theoretical guarantees of progress in coevolutionary EAs. However, examining the genotype to phenotype map used in methods of GP which have achieved good results without archives [22] may indicate how representations inherently robust to coevolutionary pathologies can be developed.…”

Section: Conclusion and Further Workmentioning

confidence: 99%

Semantic Bias in Program Coevolution

Seaton

Miller

Clarke

2013

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. We investigate the occurrence of two pathological coevolutionary behaviours, specifically disengagement and cycling, in GP systems. An empirical analysis is carried out using constructed GP problems and a historical pursuit and evasion task, the Game of Tag. The effect of semantic bias on the likelihood of pathologies and performance in a coevolutionary context is examined. We present findings correlating semantic locality in the genotype to phenotype map to disengagement and cycling in a minimal competitive coevolutionary algorithm.

show abstract

Winning Ant Wars: Evolving a Human-Competitive Game Strategy Using Fitnessless Selection

Cited by 12 publications

References 7 publications

Coevolutionary Temporal Difference Learning for Othello

Coevolutionary Temporal Difference Learning for Othello

Fitnessless coevolution

Semantic Bias in Program Coevolution

Contact Info

Product

Resources

About