Hierarchical Optimistic Region Selection driven by Curiosity - Archive ouverte HAL Access content directly
Preprints, Working Papers, ... Year :

Hierarchical Optimistic Region Selection driven by Curiosity

Abstract

This paper aims to take a step forwards making the term ''intrinsic motivation'' from reinforcement learning theoretically well founded, focusing on curiosity-driven learning. To that end, we consider the setting where, a fixed partition \P of a continuous space \X being given, and a process \nu defined on \X being unknown, we are asked to sequentially decide which cell of the partition to select as well as where to sample \nu in that cell, in order to minimize a loss function that is inspired from previous work on curiosity-driven learning. The loss on each cell consists of one term measuring a simple worst case quadratic sampling error, and a penalty term proportional to the range of the variance in that cell. The corresponding problem formulation extends the setting known as active learning for multi-armed bandits to the case when each arm is a continuous region, and we show how an adaptation of recent algorithms for that problem and of hierarchical optimistic sampling algorithms for optimization can be used in order to solve this problem. The resulting procedure, called Hierarchical Optimistic Region SElection driven by Curiosity (HORSE.C) is provided together with a finite-time regret analysis.
Fichier principal
Vignette du fichier
horsec_nips_supplementary.pdf (348 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-00740418 , version 1 (25-10-2012)

Identifiers

  • HAL Id : hal-00740418 , version 1

Cite

Odalric-Ambrym Maillard. Hierarchical Optimistic Region Selection driven by Curiosity. 2012. ⟨hal-00740418⟩

Collections

INSMI
67 View
84 Download

Share

Gmail Facebook Twitter LinkedIn More