Multi-Agent Image Classification via Reinforcement Learning
This addresses decentralized classification for multi-agent systems, but it appears incremental as it applies known RL techniques to a specific setup.
The paper tackles image classification using multiple mobile agents with partial observations, proposing a decentralized reinforcement learning framework with local belief formation and neighbor communication. Experimental results on MNIST demonstrate its effectiveness.
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.