Emergence of Roles in Robotic Teams with Model Sharing and Limited Communication
This incremental approach reduces resource usage for applications like logistics and environmental monitoring, but is domain-specific to robotic teams.
The paper tackles the problem of high computational and energy demands in multi-agent foraging systems by proposing a reinforcement learning strategy where learning is centralized to one agent and its model is periodically shared with non-learning agents, resulting in agents developing differentiated roles without explicit communication.
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.