Work

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

Year: 2025

Type: conference-paper

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.

Source: IEEE International Conference on Acoustics Speech and Signal Processing

DOI: 10.1109/icassp49660.2025.10889252

Authors: Ainur Zhaikhan, Ali H. Sayed

Institution: École Polytechnique Fédérale de Lausanne

Language: English

Topic: Reinforcement Learning in Robotics

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W4408355388

FWCI: 1.982

Cites: 13

Cited by: 2

Related to: 10