Abstract
This paper introduces and tests Action Planning mechanism in the Anticipatory Classifier System ACS2. Action Planning implies goal-directed learning and bidirectional search to strengthen reliable classifiers. It is shown that it can speed up the process of gaining knowledge about the learned environment. Experiments were performed over three environments (Hand-Eye, Maze and Taxi) extended with custom goal-generator functions.
The work was supported by statutory grant of the Wrocław University of Science and Technology, Poland.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Brockman G, Cheung V, Pettersson L, Schneider J, Schulman J, Tang J, Zaremba W (2016) OpenAI Gym. ArXiv e-prints
Butz M, Stolzmann W (1999) Action-planning in anticipatory classifier systems. In: Proceedings of the 1999 genetic and evolutionary computation conference workshop program, pp 242–249
Butz MV (2002) Anticipatory learning classifier systems, vol 4. Springer, New York
Butz MV, Goldberg DE (2003) Generalized state values in an anticipatory learning classifier system. In: Anticipatory behavior in adaptive learning systems. Springer, pp 282–301
Butz MV, Stolzmann W (2002) An algorithmic description of ACS2. In: Lanzi PL, Stolzmann W, Wilson SW (eds) Advances in learning classifier systems. Springer, Heidelberg, pp 211–229
Dietterich TG (2000) Hierarchical reinforcement learning with the MAXQ value function decomposition. J Artif Intell Res 13:227–303
Hoffmann J (2016) Vorhersage und Erkenntnis. Universität Würzburg
Kozlowski N, Unold O (2018) Integrating anticipatory classifier systems with OpenAI gym. In: Proceedings of the genetic and evolutionary computation conference companion. ACM, pp 1410–1417
Stolzmann W (1997) Antizipative classifier systems. Ph.D. thesis. Fachbereich Mathematik/Informatik, University of Osnabrück
Stolzmann W, Butz M (1999) Latent learning and action planning in robots with anticipatory classifier systems. In: International workshop on learning classifier systems. Springer, pp 301–317
Unold O, Tuszyński K (2008) Mining knowledge from data using anticipatory classifier system. Knowl-Based Syst 21(5):363–370
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Switzerland AG
About this paper
Cite this paper
Unold, O., Rogula, E., Kozłowski, N. (2020). Introducing Action Planning to the Anticipatory Classifier System ACS2. In: Burduk, R., Kurzynski, M., Wozniak, M. (eds) Progress in Computer Recognition Systems. CORES 2019. Advances in Intelligent Systems and Computing, vol 977. Springer, Cham. https://doi.org/10.1007/978-3-030-19738-4_27
Download citation
DOI: https://doi.org/10.1007/978-3-030-19738-4_27
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-19737-7
Online ISBN: 978-3-030-19738-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)