# Multi-Agent Image Classification via Reinforcement Learning

## TL;DR

This paper introduces a multi-agent reinforcement learning framework for decentralized image classification, where mobile agents collaboratively gather and exchange partial observations to accurately classify images over time.

## Contribution

It presents a novel network architecture enabling agents to form local beliefs, exchange information, and learn decentralized classification strategies using reinforcement learning.

## Key findings

- Effective classification on MNIST dataset
- Decentralized consensus improves accuracy
- Agents successfully share information to enhance decision-making

## Abstract

We investigate a classification problem using multiple mobile agents capable of collecting (partial) pose-dependent observations of an unknown environment. The objective is to classify an image over a finite time horizon. We propose a network architecture on how agents should form a local belief, take local actions, and extract relevant features from their raw partial observations. Agents are allowed to exchange information with their neighboring agents to update their own beliefs. It is shown how reinforcement learning techniques can be utilized to achieve decentralized implementation of the classification problem by running a decentralized consensus protocol. Our experimental results on the MNIST handwritten digit dataset demonstrates the effectiveness of our proposed framework.