Dealing with Large MDPs, case study of waterway networks supervision

Guillaume Desquesnes (1) , Guillaume Lozenguez (1) , Arnaud Doniec (1) , Eric Duviella (1)

1 Mines Douai EMD - École des Mines de Douai

Inland waterway networks are likely to go through heavy changes due to a will in increasing the boat traffic and to the effects of climate change. Those changes would lead to a greater need of an automatic and intelligent planning for an adaptive and resilient water management. A representative model is proposed and tested using MDPs with promising results on the water management optimization. The proposed model permits to coordinate multiple entities over multiple time steps in order to avoid a flood in the waterway network. However, the proposed model suffers a lack of scalability and is unable to represent a real case application. The advantages and limitations of several approaches of the literature are discussed according to our case study.

Mots clés: Markov Decision Process; Inland waterway network; Large model

Domaines: Intelligence artificielle [cs.AI]; Système multi-agents [cs.MA]; Modélisation et simulation

Guillaume Desquesnes, Guillaume Lozenguez, Arnaud Doniec, Eric Duviella. Dealing with Large MDPs, case study of waterway networks supervision. 14th International Conference on Practical Applications of Agents and Multi-Agent Systems, PAAMS, Jun 2016, Séville, Spain. pp.48-59, ⟨10.1007/978-3-319-39324-7_5⟩. ⟨hal-01333408⟩