GA-based Action Learning

Satoshi Yonemoto

Abstract

This paper describes a GA-based action learning framework. First, we propose a GA-based method for action learning. In this work, GA is used to learn perception-action rules that cannot be represented as genes directly. The chromosome with the best fitness (elitist) acquires the perception-action rules through the learning process. And then, we extend the method to action series learning. In the extended method, action series can be treated as one of perception-action rules. We present the experimental results of three controllers (simple game AI testbed) using the GA-based action learning framework.

References

  1. Togelius, Julian, Sergey Karakovskiy, and Robin Baumgarten, 2010. The 2009 mario ai competition, Evolutionary Computation (CEC), IEEE Congress on. IEEE.
  2. Shaker, Noor, et al., 2011. The 2010 Mario AI championship: Level generation track, Computational Intelligence and AI in Games, IEEE Transactions on 3.4 : 332-347.
  3. Yannakakis, Geogios N, 2012. Game AI revisited. Proceedings of the 9th conference on Computing Frontiers. ACM.
  4. Gu, Dongbing, et al., 2003. GA-based learning in behaviour based robotics, Computational Intelligence in Robotics and Automation. IEEE International Symposium on 3.
  5. Brooks, Rodney A., 2014. The role of learning in autonomous robots, Proceedings of the fourth annual workshop on Computational learning theory.
  6. Siegwart, Roland, Illah Reza Nourbakhsh, and Davide Scaramuzza, 2011. Introduction to autonomous mobile robots. MIT press.
  7. Kuffner Jr, James J, 1998. Goal-directed navigation for animated characters using real-time path planning and control, Modelling and Motion Capture Techniques for Virtual Environments. Springer Berlin Heidelberg, 171-186.
  8. Mnih, Volodymyr, et al., 2015. Human-level control through deep reinforcement learning, Nature 518.7540: 529-533.
Download


Paper Citation


in Harvard Style

Yonemoto S. (2015). GA-based Action Learning . In Proceedings of the 7th International Joint Conference on Computational Intelligence - Volume 1: ECTA, ISBN 978-989-758-157-1, pages 293-298. DOI: 10.5220/0005613902930298


in Bibtex Style

@conference{ecta15,
author={Satoshi Yonemoto},
title={GA-based Action Learning},
booktitle={Proceedings of the 7th International Joint Conference on Computational Intelligence - Volume 1: ECTA,},
year={2015},
pages={293-298},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0005613902930298},
isbn={978-989-758-157-1},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 7th International Joint Conference on Computational Intelligence - Volume 1: ECTA,
TI - GA-based Action Learning
SN - 978-989-758-157-1
AU - Yonemoto S.
PY - 2015
SP - 293
EP - 298
DO - 10.5220/0005613902930298