Examensarbeten för masterexamen // Master Theses
Länka till denna samling:
Browse
Browsar Examensarbeten för masterexamen // Master Theses efter Ämnesord "abstraction"
Visar 1 - 1 av 1
Sökresultat per sida
Sortera efter
- PostLearning Abstractions via Reinforcement Learning(2022) JERGÉUS, ERIK; KARLSSON OINONEN, LEO; Chalmers tekniska högskola / Institutionen för data och informationsteknik; Dubhashi, Devdatt; Johansson, MoaIn 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.