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

2 code implementations • 10 Apr 2024 • Zeno Woywood, Jasper I. Wiltfang, Julius Luy, Tobias Enders, Maximilian Schiffer

We study a sequential decision-making problem for a profit-maximizing operator of an Autonomous Mobility-on-Demand system.

Decision Making

Strategic Workforce Planning in Crowdsourced Delivery with Hybrid Driver Fleets

no code implementations • 28 Nov 2023 • Julius Luy, Gerhard Hiermann, Maximilian Schiffer

Against this background, we jointly study a workforce planning problem that considers fixed drivers (FDs) and the temporal development of the crowdsourced driver (CD) fleet over a long-term time horizon.

Dynamic Neighborhood Construction for Structured Large Discrete Action Spaces

1 code implementation • 31 May 2023 • Fabian Akkerman, Julius Luy, Wouter van Heeswijk, Maximilian Schiffer

Large discrete action spaces (LDAS) remain a central challenge in reinforcement learning.

Benchmarking Recommendation Systems