Hittauppsatser.se

Uppsats

Learning Abstractions via Reinforcement Learning

H

JERGÉUS, ERIK, KARLSSON OINONEN, LEO

Chalmers tekniska högskola / Institutionen för data och informationsteknik

Publicerad: 2022

Språk: Engelska

Nyckelord

klicka för att söka
⌕AI⌕communication⌕RL⌕multi-agent⌕neuro-symbolic⌕MARL⌕Abstraction⌕DreamCoder

Sammanfattning

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.

Information

Författare
JERGÉUS, ERIK, KARLSSON OINONEN, LEO
Lärosäte / institution
Chalmers tekniska högskola / Institutionen för data och informationsteknik
Publiceringsdatum
2022
Uppsatstyp
H
Språk
Engelska
Nyckelord
⌕AI⌕communication⌕RL⌕multi-agent⌕neuro-symbolic⌕MARL⌕Abstraction⌕DreamCoder

Utforska vidare

Liknande uppsatser

Uppsatser med liknande ämnen och nyckelord.