Saved in:
Bibliographic Details
Main Author: Andreas Matt
Format: Artículo científico
Language:en
Published: Asociación Española para la Inteligencia Artificial 2003
Subjects:
Online Access:https://www.redalyc.org/articulo.oa?id=92572107
Tags: Add Tag
No Tags, Be the first to tag this record!
Table of Contents:
  • Generalization over environments in reinforcement learning Andreas Matt Georg Regensburger Ingeniería generalization obstacle avoidance reinforcement learning multiple environments and objectives We discuss the problem of reinforcement learning in one environment and applying the policy obtainedto other environments. We first state a method to evaluate the utility of a policy. Then we propose ageneral model to apply one policy to different environments and compare them. To illustrate the theorywe present examples for an obstacle avoidance behavior in various block world environments 2003 artículo científico 1137-3601 https://www.redalyc.org/articulo.oa?id=92572107 en http://www.redalyc.org/revista.oa?id=925 Inteligencia Artificial. Revista Iberoamericana de Inteligencia Artificial application/pdf Asociación Española para la Inteligencia Artificial Inteligencia Artificial. Revista Iberoamericana de Inteligencia Artificial (España) Num.21 Vol.7