2024/11/12 by Maria Zampella, Urtzi Otamendi, Zampella, Maria +11
Engineering · Mathematics · Psychology · #Advanced Manufacturing and Logistics Optimization #Artificial intelligence #Assembly Line Balancing Optimization #Computer science #Machine learning #Mathematical optimization #Mathematics #Parallel computing #Psychology #Reinforcement #Reinforcement learning #Scheduling (production processes) #Scheduling and Optimization Algorithms #Social psychology
paper · pdf · doi:10.48550/arxiv.2411.07634
openalex publication_date 2024/11/12 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05
Scheduling problems pose significant challenges in resource, industry, and operational management. This paper addresses the Unrelated Parallel Machine Scheduling Problem (UPMS) with setup times and resources using a Multi-Agent Reinforcement Learning (MARL) approach. The study introduces the Reinforcement Learning environment and conducts empirical analyses, comparing MARL with Single-Agent algorithms. The experiments employ various deep neural network policies for single- and Multi-Agent approaches. Results demonstrate the efficacy of the Maskable extension of the Proximal Policy Optimization (PPO) algorithm in Single-Agent scenarios and the Multi-Agent PPO algorithm in Multi-Agent setups. While Single-Agent algorithms perform adequately in reduced scenarios, Multi-Agent approaches reveal challenges in cooperative learning but a scalable capacity. This research contributes insights into applying MARL techniques to scheduling optimization, emphasizing the need for algorithmic sophistication balanced with scalability for intelligent scheduling solutions.