SYLGMAApr 10, 2024

Multi-Agent Soft Actor-Critic with Coordinated Loss for Autonomous Mobility-on-Demand Fleet Control

arXiv:2404.06975v24 citationsh-index: 4LION
AI Analysis

This addresses fleet control efficiency for autonomous mobility-on-demand operators, representing an incremental improvement with specific gains.

The paper tackled the problem of optimizing vehicle-to-request dispatching for autonomous mobility-on-demand fleets by proposing a multi-agent Soft Actor-Critic algorithm with coordinated loss, achieving performance improvements of up to 12.9% for dispatching and up to 38.9% with integrated rebalancing compared to state-of-the-art benchmarks.

We study a sequential decision-making problem for a profit-maximizing operator of an autonomous mobility-on-demand system. Optimizing a central operator's vehicle-to-request dispatching policy requires efficient and effective fleet control strategies. To this end, we employ a multi-agent Soft Actor-Critic algorithm combined with weighted bipartite matching. We propose a novel vehicle-based algorithm architecture and adapt the critic's loss function to appropriately consider coordinated actions. Furthermore, we extend our algorithm to incorporate rebalancing capabilities. Through numerical experiments, we show that our approach outperforms state-of-the-art benchmarks by up to 12.9% for dispatching and up to 38.9% with integrated rebalancing.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes