A Fitted-Q Algorithm for Budgeted MDPs - Archive ouverte HAL
Conference Papers Year : 2018

A Fitted-Q Algorithm for Budgeted MDPs

Abstract

We address the problem of budgeted reinforcement learning, in continuous state-space, using a batch of transitions. To this extend, we introduce a novel algorithm called Budgeted Fitted-Q (BFTQ). Benchmarks show that BFTQ performs as well as a regular Fitted-Q algorithm in a continuous 2-D world but also allows one to choose the right amount of budget that fits to a given task without the need of engineering the rewards. We believe that the general principles used to design BFTQ can be applied to extend others classical reinforcement learning algorithms for budgeted oriented applications.
Fichier principal
Vignette du fichier
ewrl_14_2018_paper_67.pdf (7.3 Mo) Télécharger le fichier
Origin Files produced by the author(s)
Loading...

Dates and versions

hal-01928092 , version 1 (20-11-2018)

Identifiers

  • HAL Id : hal-01928092 , version 1

Cite

Nicolas Carrara, Romain Laroche, Jean-Léon Bouraoui, Tanguy Urvoy, Olivier Pietquin. A Fitted-Q Algorithm for Budgeted MDPs. EWRL 2018 - 14th European workshop on Reinforcement Learning, Oct 2018, Lille, France. ⟨hal-01928092⟩
109 View
80 Download

Share

More