Towards Learning Abstractions via Reinforcement Learning
This addresses communication efficiency in multi-agent systems, but it is incremental as it builds on existing neuro-symbolic approaches.
The paper tackles the problem of synthesizing efficient communication schemes in multi-agent systems by combining symbolic methods with reinforcement learning to extend language with novel concepts, resulting in agents converging more quickly on a collaborative construction task.
In this paper we take the first steps in studying a new approach to synthesis of efficient communication schemes in multi-agent systems, trained via reinforcement learning. We combine symbolic methods with machine learning, in what is referred to as a neuro-symbolic system. The agents are not restricted to only use initial primitives: reinforcement learning is interleaved with steps to extend the current language with novel higher-level concepts, allowing generalisation and more informative communication via shorter messages. We demonstrate that this approach allow agents to converge more quickly on a small collaborative construction task.