Exploring Multi-Agent Reinforcement Learning for Unrelated Parallel Machine Scheduling
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866910695504740352 |
|---|---|
| author | Zampella, Maria Otamendi, Urtzi Belaunzaran, Xabier Artetxe, Arkaitz Olaizola, Igor G. Longo, Giuseppe Sierra, Basilio |
| author_facet | Zampella, Maria Otamendi, Urtzi Belaunzaran, Xabier Artetxe, Arkaitz Olaizola, Igor G. Longo, Giuseppe Sierra, Basilio |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2411_07634 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Exploring Multi-Agent Reinforcement Learning for Unrelated Parallel Machine Scheduling Zampella, Maria Otamendi, Urtzi Belaunzaran, Xabier Artetxe, Arkaitz Olaizola, Igor G. Longo, Giuseppe Sierra, Basilio Artificial Intelligence Machine Learning Multiagent Systems Neural and Evolutionary Computing I.2.1; I.2.11; I.2.8 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. |
| title | Exploring Multi-Agent Reinforcement Learning for Unrelated Parallel Machine Scheduling |
| topic | Artificial Intelligence Machine Learning Multiagent Systems Neural and Evolutionary Computing I.2.1; I.2.11; I.2.8 |
| url | https://arxiv.org/abs/2411.07634 |