SULFR: Simulation of Urban Logistic For Reinforcement

Guillaume Bono 1, 2 Jilles Steeve Dibangoye 1 Laëtitia Matignon 1, 3 Florian Pereyron 4 Olivier Simonin 1
1 CHROMA - Robots coopératifs et adaptés à la présence humaine en environnements dynamiques
CITI - CITI Centre of Innovation in Telecommunications and Integration of services, Inria Grenoble - Rhône-Alpes
2 CITI - CITI Centre of Innovation in Telecommunications and Integration of services
3 SMA - Systèmes Multi-Agents
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
4 Volvo Group
Abstract : In urban logistics, various sources of uncertainty can invalidate pre-planned routes. In this context, a routing strategy that uses available information from the environment could help improve the overall performance of the routing process by dynamically choosing the next client at the online execution time. While static and deterministic testbeds for vehicle routing exist, their stochastic and dynamic counterparts are still missing. This paper proposes an interface to the microtraffic simulation package SUMO that implement a generative model of stochastic and dynamic vehicle routing problems. We formalize the latter using a reinforcement learning framework for semi-Markov decision processes. The resulting testbeds make it possible to compare single- and multi-agent reinforcement learning algorithms in customizable routing environments. We report our preliminary tests to evaluate a hand-crafted policy on some basic scenarios.
Document type :
Conference papers
Complete list of metadatas

Cited literature [21 references]  Display  Hide  Download
https://hal.inria.fr/hal-01847773
Contributor : Guillaume Bono <>
Submitted on : Friday, September 7, 2018 - 1:21:33 PM
Last modification on : Wednesday, November 20, 2019 - 2:38:30 AM

File

gbono_pgmrl18.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01847773, version 2

Collections

CNRS | EC-LYON | TDS-MACS | UNIV-LYON2 | UNIV-LYON1 | INSA-LYON | INRIA | LIRIS | CITI | INSA-GROUPE | LABEXIMU | UDL

Citation

Guillaume Bono, Jilles Steeve Dibangoye, Laëtitia Matignon, Florian Pereyron, Olivier Simonin. SULFR: Simulation of Urban Logistic For Reinforcement. PGMRL 2018Workshop on Prediction and Generative Modeling in Reinforcement Learning, Jul 2018, Stockholm, Sweden. pp.1-5. ⟨hal-01847773v2⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

436

Files downloads

213

 

 

Contact

archive-ouverte@inria.fr