A connectionist architecture that adpats its representation to complex tasks - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2002

A connectionist architecture that adpats its representation to complex tasks

Bruno Scherrer

Abstract

This paper presents an original connectionist architecture that is capable of adapting its representation to one or various reinforcement problems. We briefly describe the generic reinforcement learning theory it is based on. We focus on distributed algorithms that enables efficient planning. In this specific framework, we define the notion of task-specialisation and propose a procedure for adapting a task model without increasing its complexity. It consists in a high-level learning of representation in problems with possibly delayed reinforcements. We show that such a single architecture can adapt to multiple tasks. Finally we stress its connectionist nature: most computations can be distributed and done in parallel. We illustrate and evaluate this adaptation paradigm on a navigation continuous-space environment.
No file

Dates and versions

inria-00100735 , version 1 (26-09-2006)

Identifiers

  • HAL Id : inria-00100735 , version 1

Cite

Bruno Scherrer. A connectionist architecture that adpats its representation to complex tasks. International Joint Conference on Neural Networks - IJCNN 2002, 2002, Hilton hawaiian Village, Honolulu, HI, 6 p. ⟨inria-00100735⟩
71 View
0 Download

Share

Gmail Facebook X LinkedIn More