Constrained multiagent reinforcement learning for large agent population
Learning control policies for a large number of agents in a decentralized setting is challenging due to partial observability, uncertainty in the environment, and scalability challenges. While several scalable multiagent RL (MARL) methods have been proposed, relatively few approaches exist for large...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | text |
| Language: | English |
| Published: |
Institutional Knowledge at Singapore Management University
2023
|
| Subjects: | |
| Online Access: | https://ink.library.smu.edu.sg/sis_research/8091 https://ink.library.smu.edu.sg/context/sis_research/article/9094/viewcontent/978_3_031_26412_2_12_pv.pdf |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Singapore Management University |
| Language: | English |
| Summary: | Learning control policies for a large number of agents in a decentralized setting is challenging due to partial observability, uncertainty in the environment, and scalability challenges. While several scalable multiagent RL (MARL) methods have been proposed, relatively few approaches exist for large scale constrained MARL settings. To address this, we first formulate the constrained MARL problem in a collective multiagent setting where interactions among agents are governed by the aggregate count and types of agents, and do not depend on agents’ specific identities. Second, we show that standard Lagrangian relaxation methods, which are popular for single agent RL, do not perform well in constrained MARL settings due to the problem of credit assignment—how to identify and modify behavior of agents that contribute most to constraint violations (and also optimize primary objective alongside)? We develop a fictitious MARL method that addresses this key challenge. Finally, we evaluate our approach on two large-scale real-world applications: maritime traffic management and vehicular network routing. Empirical results show that our approach is highly scalable, can optimize the cumulative global reward and effectively minimize constraint violations, while also being significantly more sample efficient than previous best methods. |
|---|