Multi-Agent Reinforcement Learning in Partially Observable Environments Using Social Learning

Ainur Zhaikhan; Ali H. Sayed

ICASSP 2025accepted0 citations

Multi-Agent Reinforcement Learning in Partially Observable Environments Using Social Learning

Abstract

This work employs a social learning strategy to estimate the global state in a partially observable multi-agent reinforcement learning (MARL) setting. We prove that the proposed methodology can achieve results within an ε-neighborhood of the solution for a fully observable setting, provided that a sufficient number of social learning updates are performed. We illustrate the results through computer simulations.

BibTeX

@inproceedings{icassp2025_multiagentreinfo,
  title = {Multi-Agent Reinforcement Learning in Partially Observable Environments Using Social Learning},
  author = {Ainur Zhaikhan and Ali H. Sayed},
  booktitle = {ICASSP 2025},
  year = {2025}
}