Using Game-Theory and Decentralization to Scale Multi-Agent Reinforcement Learning Models

When we think about training or learning processes in deep learning solution we typically visualize centralized models. In those architectures a series of central nodes collect and curate datasets which are used to train the models that are deployed across different nodes in a network. Even in distributed scenarios such as multi-agent reinforcement learning(MARL) that can include tens of thousands of nodes running a model the learning models rely on a handful of centralized nodes. Centralized learning is conceptually simple to implement but incredibly hard to scale. Imagine an internet of things(IOT) scenario with hundreds of thousands of devices collecting data and executing a reinforcement learning model.