Skip to Main content Skip to Navigation
Conference papers

Policies Generalization in Reinforcement Learning using Galois Partitions Lattices

Abstract : The generalization of policies in reinforcement learning is a main issue, both from the theoretical model point of view and for their applicability. However, generalizing from a set of examples or searching for regularities is a problem which has already been intensively studied in machine learning. Our work uses techniques in which generalizations are constrained by a language bias, in order to regroup similar states. Such generalizations are principally based on the properties of concept lattices. To guide the possible groupings of similar environment's states, we propose a general algebraic framework, considering the generalization of policies through a set partition of the states and using a language bias as an a priori knowledge. We give an application as an example of our approach by proposing and experimenting a bottom-up algorithm.
Document type :
Conference papers
Complete list of metadatas

Cited literature [14 references]  Display  Hide  Download

https://hal-lirmm.ccsd.cnrs.fr/lirmm-00187164
Contributor : Martine Peridier <>
Submitted on : Wednesday, September 4, 2019 - 8:15:18 PM
Last modification on : Wednesday, September 4, 2019 - 8:15:49 PM
Document(s) archivé(s) le : Thursday, February 6, 2020 - 7:09:27 AM

File

Ricordeau.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : lirmm-00187164, version 1

Collections

Citation

Marc Ricordeau, Michel Liquière. Policies Generalization in Reinforcement Learning using Galois Partitions Lattices. CLA: Concept Lattices and their Applications, Oct 2007, Montpellier, France. pp.286-297. ⟨lirmm-00187164⟩

Share

Metrics

Record views

203

Files downloads

24