Hybrid Multi-agent Deep Reinforcement Learning for Autonomous Mobility on Demand Systems

Tobias Enders, James Harrison, Marco Pavone, Maximilian Schiffer

Publikation: Beitrag in FachzeitschriftKonferenzartikelBegutachtung


We consider the sequential decision-making problem of making proactive request assignment and rejection decisions for a profit-maximizing operator of an autonomous mobility on demand system. We formalize this problem as a Markov decision process and propose a novel combination of multi-agent Soft Actor-Critic and weighted bipartite matching to obtain an anticipative control policy. Thereby, we factorize the operator's otherwise intractable action space, but still obtain a globally coordinated decision. Experiments based on real-world taxi data show that our method outperforms state of the art benchmarks with respect to performance, stability, and computational tractability.

Seiten (von - bis)1284-1296
FachzeitschriftProceedings of Machine Learning Research
PublikationsstatusVeröffentlicht - 2023
Veranstaltung5th Annual Conference on Learning for Dynamics and Control, L4DC 2023 - Philadelphia, USA/Vereinigte Staaten
Dauer: 15 Juni 202316 Juni 2023


Untersuchen Sie die Forschungsthemen von „Hybrid Multi-agent Deep Reinforcement Learning for Autonomous Mobility on Demand Systems“. Zusammen bilden sie einen einzigartigen Fingerprint.

Dieses zitieren