Hippocampal formation breaks combinatorial explosion for reinforcement learning: A conjecture

Research output: Chapter in Book/Report/Conference proceedingConference contribution

1 Citation (Scopus)

Abstract

There is surmounting evidence that reinforcement learning (RL) is a good model for the dopamine system of the brain and the prefrontal cortex. RL is also promising from the algorithmic point of view, because recent factored RL algorithms have favorable convergence and scaling properties and can counteract the curse of dimensionality problem, the major obstacle of practical applications of RL methods. Learning in navigation tasks then separates (i) to the search and the encoding of the factors, such as position, direction, and speed, and (ii) to the optimization of RL decision making by using these factors. We conjecture that the main task of the hippocampal formation is to separate factors and encode into neocortical areas the different low-dimensional conjunctive representations of them to suit factored RL value estimation. The mathematical framework is sketched. It includes convergent factored RL model and autoregressive (AR) hidden process model that finds factors including the hidden causes. The AR model is mapped to the hippocampal formation.

Original languageEnglish
Title of host publicationBiologically Inspired Cognitive Architectures - Papers from the AAAI Fall Symposium, Technical Report
PublisherAmerican Association for Artificial Intelligence
Pages105-110
Number of pages6
ISBN (Print)9781577353966
Publication statusPublished - Jan 1 2008
Event2008 AAAI Fall Symposium - Arlington, VA, United States
Duration: Nov 7 2008Nov 9 2008

Publication series

NameAAAI Fall Symposium - Technical Report
VolumeFS-08-04

Other

Other2008 AAAI Fall Symposium
CountryUnited States
CityArlington, VA
Period11/7/0811/9/08

ASJC Scopus subject areas

  • Engineering(all)

Fingerprint Dive into the research topics of 'Hippocampal formation breaks combinatorial explosion for reinforcement learning: A conjecture'. Together they form a unique fingerprint.

  • Cite this

    Ĺrincz, A. (2008). Hippocampal formation breaks combinatorial explosion for reinforcement learning: A conjecture. In Biologically Inspired Cognitive Architectures - Papers from the AAAI Fall Symposium, Technical Report (pp. 105-110). (AAAI Fall Symposium - Technical Report; Vol. FS-08-04). American Association for Artificial Intelligence.