Policies Generalization in Reinforcement Learning using Galois Partitions Lattices - LIRMM - Laboratoire d’Informatique, de Robotique et de Microélectronique de Montpellier Access content directly
Conference Papers Year : 2007

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.
Fichier principal
Vignette du fichier
Ricordeau.pdf (603.97 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

lirmm-00187164 , version 1 (04-09-2019)

Identifiers

  • HAL Id : lirmm-00187164 , version 1

Cite

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⟩
141 View
40 Download

Share

Gmail Facebook X LinkedIn More