Modeling Sensorimotor Coordination as Multi-Agent Reinforcement Learning with Differentiable Communication

TL;DR

This paper introduces a modular multi-agent reinforcement learning framework with differentiable communication to model sensorimotor coordination, enabling heterogeneous agents to cooperate on complex tasks, with implications for neuroscience and AI.

Contribution

It presents a novel modular architecture that models the neocortex as a collection of heterogeneous agents, extending multi-agent RL to more complex, brain-inspired systems.

Findings

Proof-of-concept demonstration of the architecture

Modeling sensorimotor coordination as multi-agent RL

Potential for understanding brain functions and developing intelligent systems

Abstract

Multi-agent reinforcement learning has shown promise on a variety of cooperative tasks as a consequence of recent developments in differentiable inter-agent communication. However, most architectures are limited to pools of homogeneous agents, limiting their applicability. Here we propose a modular framework for learning complex tasks in which a traditional monolithic agent is framed as a collection of cooperating heterogeneous agents. We apply this approach to model sensorimotor coordination in the neocortex as a multi-agent reinforcement learning problem. Our results demonstrate proof-of-concept of the proposed architecture and open new avenues for learning complex tasks and for understanding functional localization in the brain and future intelligent systems.