• Recherche,

"The Exploration-Exploitation Dilemma on Structured Environments" , colloque de l'IRIT

le 16 décembre 2014

Manufacture des Tabacs
Salle ME303

Filipo Studzinski Perotto nous présentera ses travaux sur "The Exploration-Exploitation Dilemma on Structured Environments"

Filipo Studzinski Perotto est enseignant chercheur à l'Université Toulouse 1 Capitole. Il donnera cette conférence entièrement en anglais.

Abstract : Balancing exploratory and exploitative behavior is an essential dilemma faced by adaptive agents. The problem of finding a good trade-off between exploration (learn new things) and exploitation (act optimally based on the current knowledge) has been largely studied for Markov Decision Processes (MDP), but it is relatively new for Factored MDPs. In this presentation we present a strategy to solve the exploration-exploitation dilemma coupled with a learning mechanism designed to learn the FMDP parameters. The solution consists in explicitly creating two different policies, each one designed for exploring or exploiting.
Mis à jour le 17 décembre 2014