Towards Learning Abstractions via Reinforcement Learning
Erik Jergéus, Leo Karlsson Oinonen, Emil Carlsson, Moa Johansson. Published in AIC 2022, 8th International Workshop on Artificial Intelligence and Cognition, 2022
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.