POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding
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_ | 1866910906050412544 |
|---|---|
| author | Skrynnik, Alexey Andreychuk, Anton Borzilov, Anatolii Chernyavskiy, Alexander Yakovlev, Konstantin Panov, Aleksandr |
| author_facet | Skrynnik, Alexey Andreychuk, Anton Borzilov, Anatolii Chernyavskiy, Alexander Yakovlev, Konstantin Panov, Aleksandr |
| contents | Multi-agent reinforcement learning (MARL) has recently excelled in solving challenging cooperative and competitive multi-agent problems in various environments, typically involving a small number of agents and full observability. Moreover, a range of crucial robotics-related tasks, such as multi-robot pathfinding, which have traditionally been approached with classical non-learnable methods (e.g., heuristic search), are now being suggested for solution using learning-based or hybrid methods. However, in this domain, it remains difficult, if not impossible, to conduct a fair comparison between classical, learning-based, and hybrid approaches due to the lack of a unified framework that supports both learning and evaluation. To address this, we introduce POGEMA, a comprehensive set of tools that includes a fast environment for learning, a problem instance generator, a collection of predefined problem instances, a visualization toolkit, and a benchmarking tool for automated evaluation. We also introduce and define an evaluation protocol that specifies a range of domain-related metrics, computed based on primary evaluation indicators (such as success rate and path length), enabling a fair multi-fold comparison. The results of this comparison, which involves a variety of state-of-the-art MARL, search-based, and hybrid methods, are presented. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_14931 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding Skrynnik, Alexey Andreychuk, Anton Borzilov, Anatolii Chernyavskiy, Alexander Yakovlev, Konstantin Panov, Aleksandr Machine Learning Artificial Intelligence Multiagent Systems Multi-agent reinforcement learning (MARL) has recently excelled in solving challenging cooperative and competitive multi-agent problems in various environments, typically involving a small number of agents and full observability. Moreover, a range of crucial robotics-related tasks, such as multi-robot pathfinding, which have traditionally been approached with classical non-learnable methods (e.g., heuristic search), are now being suggested for solution using learning-based or hybrid methods. However, in this domain, it remains difficult, if not impossible, to conduct a fair comparison between classical, learning-based, and hybrid approaches due to the lack of a unified framework that supports both learning and evaluation. To address this, we introduce POGEMA, a comprehensive set of tools that includes a fast environment for learning, a problem instance generator, a collection of predefined problem instances, a visualization toolkit, and a benchmarking tool for automated evaluation. We also introduce and define an evaluation protocol that specifies a range of domain-related metrics, computed based on primary evaluation indicators (such as success rate and path length), enabling a fair multi-fold comparison. The results of this comparison, which involves a variety of state-of-the-art MARL, search-based, and hybrid methods, are presented. |
| title | POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding |
| topic | Machine Learning Artificial Intelligence Multiagent Systems |
| url | https://arxiv.org/abs/2407.14931 |