Analysing Factorizations of Action-Value Networks for Cooperative Multi-Agent Reinforcement Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2019
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866929638211584000 |
|---|---|
| author | Castellini, Jacopo Oliehoek, Frans A. Savani, Rahul Whiteson, Shimon |
| author_facet | Castellini, Jacopo Oliehoek, Frans A. Savani, Rahul Whiteson, Shimon |
| contents | Recent years have seen the application of deep reinforcement learning techniques to cooperative multi-agent systems, with great empirical success. However, given the lack of theoretical insight, it remains unclear what the employed neural networks are learning, or how we should enhance their learning power to address the problems on which they fail. In this work, we empirically investigate the learning power of various network architectures on a series of one-shot games. Despite their simplicity, these games capture many of the crucial problems that arise in the multi-agent setting, such as an exponential number of joint actions or the lack of an explicit coordination mechanism. Our results extend those in [4] and quantify how well various approaches can represent the requisite value functions, and help us identify the reasons that can impede good performance, like sparsity of the values or too tight coordination requirements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_1902_07497 |
| institution | arXiv |
| publishDate | 2019 |
| record_format | arxiv |
| spellingShingle | Analysing Factorizations of Action-Value Networks for Cooperative Multi-Agent Reinforcement Learning Castellini, Jacopo Oliehoek, Frans A. Savani, Rahul Whiteson, Shimon Multiagent Systems I.2.6; I.2.11 Recent years have seen the application of deep reinforcement learning techniques to cooperative multi-agent systems, with great empirical success. However, given the lack of theoretical insight, it remains unclear what the employed neural networks are learning, or how we should enhance their learning power to address the problems on which they fail. In this work, we empirically investigate the learning power of various network architectures on a series of one-shot games. Despite their simplicity, these games capture many of the crucial problems that arise in the multi-agent setting, such as an exponential number of joint actions or the lack of an explicit coordination mechanism. Our results extend those in [4] and quantify how well various approaches can represent the requisite value functions, and help us identify the reasons that can impede good performance, like sparsity of the values or too tight coordination requirements. |
| title | Analysing Factorizations of Action-Value Networks for Cooperative Multi-Agent Reinforcement Learning |
| topic | Multiagent Systems I.2.6; I.2.11 |
| url | https://arxiv.org/abs/1902.07497 |