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

Abstract

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.

Cite

Text

Enders et al. "Hybrid Multi-Agent Deep Reinforcement Learning for Autonomous Mobility on Demand Systems." Proceedings of The 5th Annual Learning for Dynamics and Control Conference, 2023.

Markdown

[Enders et al. "Hybrid Multi-Agent Deep Reinforcement Learning for Autonomous Mobility on Demand Systems." Proceedings of The 5th Annual Learning for Dynamics and Control Conference, 2023.](https://mlanthology.org/l4dc/2023/enders2023l4dc-hybrid/)

BibTeX

@inproceedings{enders2023l4dc-hybrid,
  title     = {{Hybrid Multi-Agent Deep Reinforcement Learning for Autonomous Mobility on Demand Systems}},
  author    = {Enders, Tobias and Harrison, James and Pavone, Marco and Schiffer, Maximilian},
  booktitle = {Proceedings of The 5th Annual Learning for Dynamics and Control Conference},
  year      = {2023},
  pages     = {1284-1296},
  volume    = {211},
  url       = {https://mlanthology.org/l4dc/2023/enders2023l4dc-hybrid/}
}