Towards Learning Abstractions via Reinforcement Learning

12/28/2022
by   Erik Jergéus, et al.
0

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.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset