Designing Efficient Exploration with MACS: Modules and Function Approximation

Abstract : MACS (Modular Anticipatory Classifier System) is a new Anticipatory Classifier System. With respect to its predecessors, ACS ACS2 and YACS, the latent learning process in MACS is able to take advantage of new regularities. Instead of anticipating all attributes of the perceived situations in the same classifier, MACS only anticipates one attfribute per claasifier. In this paper we describe how the model of the environment represented by the classifiers can be used to perform active exploration and how this exploration policy is aggregated with the exploitation policy. The architecture is validated expermentally. Then we draw more general principles from the architectural choices giving rise to MACS. We show that building a model of the environment can be seen as a function approximation problem which can be solved with Anticipatory Classifier Systems such as MACS, but also with accuracy-based systems like XCS or XCSF, organized into a Dyna architecture.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01532220
Contributor : Lip6 Publications <>
Submitted on : Friday, June 2, 2017 - 3:45:47 PM
Last modification on : Thursday, March 21, 2019 - 1:05:25 PM

Links full text

Identifiers

Citation

Pierre Gérard, Olivier Sigaud. Designing Efficient Exploration with MACS: Modules and Function Approximation. Genetic and Evolutionary Computation Conference 2003 (GECCO03), Jul 2003, Chicago, IL, United States. pp.1882-1893, ⟨10.1007/3-540-45110-2_85⟩. ⟨hal-01532220⟩

Share

Metrics

Record views

54