Emergence of Roles in Robotic Teams with Model Sharing and Limited Communication

TL;DR

This paper introduces a reinforcement learning approach for multi-agent robotic systems that promotes role emergence and differentiation through model sharing, reducing computational demands and enabling dynamic, communication-free role adaptation.

Contribution

The paper proposes a centralized learning strategy with periodic model sharing that fosters role development among agents without explicit communication, improving efficiency and adaptability.

Findings

Agents develop differentiated roles through reward functions.

Role differentiation occurs dynamically without explicit communication.

Approach reduces computational and energy costs.

Abstract

We present a reinforcement learning strategy for use in multi-agent foraging systems in which the learning is centralised to a single agent and its model is periodically disseminated among the population of non-learning agents. In a domain where multi-agent reinforcement learning (MARL) is the common approach, this approach aims to significantly reduce the computational and energy demands compared to approaches such as MARL and centralised learning models. By developing high performing foraging agents, these approaches can be translated into real-world applications such as logistics, environmental monitoring, and autonomous exploration. A reward function was incorporated into this approach that promotes role development among agents, without explicit directives. This led to the differentiation of behaviours among the agents. The implicit encouragement of role differentiation allows for dynamic actions in which agents can alter roles dependent on their interactions with the environment without the need for explicit communication between agents.