Towards Generalizability of Multi-Agent Reinforcement Learning in Graphs with Recurrent Message Passing
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909216293257216 |
|---|---|
| author | Weil, Jannis Bao, Zhenghua Abboud, Osama Meuser, Tobias |
| author_facet | Weil, Jannis Bao, Zhenghua Abboud, Osama Meuser, Tobias |
| contents | Graph-based environments pose unique challenges to multi-agent reinforcement learning. In decentralized approaches, agents operate within a given graph and make decisions based on partial or outdated observations. The size of the observed neighborhood limits the generalizability to different graphs and affects the reactivity of agents, the quality of the selected actions, and the communication overhead. This work focuses on generalizability and resolves the trade-off in observed neighborhood size with a continuous information flow in the whole graph. We propose a recurrent message-passing model that iterates with the environment's steps and allows nodes to create a global representation of the graph by exchanging messages with their neighbors. Agents receive the resulting learned graph observations based on their location in the graph. Our approach can be used in a decentralized manner at runtime and in combination with a reinforcement learning algorithm of choice. We evaluate our method across 1000 diverse graphs in the context of routing in communication networks and find that it enables agents to generalize and adapt to changes in the graph. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_05027 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Generalizability of Multi-Agent Reinforcement Learning in Graphs with Recurrent Message Passing Weil, Jannis Bao, Zhenghua Abboud, Osama Meuser, Tobias Multiagent Systems Artificial Intelligence Graph-based environments pose unique challenges to multi-agent reinforcement learning. In decentralized approaches, agents operate within a given graph and make decisions based on partial or outdated observations. The size of the observed neighborhood limits the generalizability to different graphs and affects the reactivity of agents, the quality of the selected actions, and the communication overhead. This work focuses on generalizability and resolves the trade-off in observed neighborhood size with a continuous information flow in the whole graph. We propose a recurrent message-passing model that iterates with the environment's steps and allows nodes to create a global representation of the graph by exchanging messages with their neighbors. Agents receive the resulting learned graph observations based on their location in the graph. Our approach can be used in a decentralized manner at runtime and in combination with a reinforcement learning algorithm of choice. We evaluate our method across 1000 diverse graphs in the context of routing in communication networks and find that it enables agents to generalize and adapt to changes in the graph. |
| title | Towards Generalizability of Multi-Agent Reinforcement Learning in Graphs with Recurrent Message Passing |
| topic | Multiagent Systems Artificial Intelligence |
| url | https://arxiv.org/abs/2402.05027 |