Approximate strategies for learning trajectories of autonomous learning agents

A. Mete Cakmakci, Can Isik

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

1 Scopus citations

Abstract

In this paper we describe a new approach to the approximate modeling of learning dynamics of autonomous learning agents for performance improvement in supervised learning. Extracted approximate model can be used to generate target trajectories from the current performance state to the final performance goal in order to `lead' the learning agent through dynamic range of the learning process. The interaction between the supervisor module and the agent can be modeled as an incentive game. Ideas introduced for the single agent case can further be extended to include multi-agents to address the coordination problem in modular learning structures.

Original languageEnglish (US)
Title of host publicationAnnual Conference of the North American Fuzzy Information Processing Society - NAFIPS
PublisherIEEE Computer Society
Pages423-427
Number of pages5
StatePublished - 1997
EventProceedings of the 1997 Annual Meeting of the North American Fuzzy Information Processing Society, NAFIPS'97 - Syracuse, NY, USA
Duration: Sep 21 1997Sep 24 1997

Other

OtherProceedings of the 1997 Annual Meeting of the North American Fuzzy Information Processing Society, NAFIPS'97
CitySyracuse, NY, USA
Period9/21/979/24/97

    Fingerprint

ASJC Scopus subject areas

  • Computer Science(all)
  • Media Technology

Cite this

Cakmakci, A. M., & Isik, C. (1997). Approximate strategies for learning trajectories of autonomous learning agents. In Annual Conference of the North American Fuzzy Information Processing Society - NAFIPS (pp. 423-427). IEEE Computer Society.