A Fitted-Q Algorithm for Budgeted MDPs

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.

Authors

• Nicolas Carrara
• Olivier Pietquin Cohere
• Romain Laroche
• Tanguy Urvoy Orange Labs Lannion
• Jean-Léon Bouraoui

Keywords

No keywords are indexed for this paper.