TY - GEN
T1 - Using Genetic Programming and Decision Trees for Team Evolution
AU - Sithungu, Siphesihle Philezwini
AU - Coulter, Duncan Anthony
AU - Ehlers, Elizabeth Marie
N1 - Publisher Copyright:
© 2019 ACM.
PY - 2019/11/23
Y1 - 2019/11/23
N2 - This paper presents work done to evolve soccer strategies through Genetic Programming. Each agent is controlled by an algorithm in the form of a decision tree to act on the environment given its percepts. Several experiments were performed and an analysis of the performance of the algorithm was documented afterwards. Experimental results showed that it is possible to implement soccer learning in a multi-agent system through Genetic Programming, although the evolution of higher-level soccer strategies is a more difficult task.
AB - This paper presents work done to evolve soccer strategies through Genetic Programming. Each agent is controlled by an algorithm in the form of a decision tree to act on the environment given its percepts. Several experiments were performed and an analysis of the performance of the algorithm was documented afterwards. Experimental results showed that it is possible to implement soccer learning in a multi-agent system through Genetic Programming, although the evolution of higher-level soccer strategies is a more difficult task.
KW - decision trees
KW - evolutionary learning
KW - genetic programming
UR - http://www.scopus.com/inward/record.url?scp=85081090349&partnerID=8YFLogxK
U2 - 10.1145/3372422.3372430
DO - 10.1145/3372422.3372430
M3 - Conference contribution
AN - SCOPUS:85081090349
T3 - ACM International Conference Proceeding Series
SP - 28
EP - 39
BT - Proceedings of the 2019 2nd International Conference on Computational Intelligence and Intelligent Systems, CIIS 2019
PB - Association for Computing Machinery
T2 - 2nd International Conference on Computational Intelligence and Intelligent Systems, CIIS 2019
Y2 - 23 November 2019 through 25 November 2019
ER -