Sökning: onr:"swepub:oai:research.chalmers.se:887658f0-4280-4f84-9ccb-fc5c02b63400" >
Towards Learning Ab...
Towards Learning Abstractions via Reinforcement Learning
-
- Jergéus, Erik (författare)
- Chalmers tekniska högskola,Chalmers University of Technology
-
- Oinonen, Leo Karlsson (författare)
- Chalmers tekniska högskola,Chalmers University of Technology
-
- Carlsson, Emil, 1995 (författare)
- Chalmers tekniska högskola,Chalmers University of Technology
-
visa fler...
-
- Johansson, Moa, 1981 (författare)
- Chalmers tekniska högskola,Chalmers University of Technology
-
visa färre...
-
(creator_code:org_t)
- 2022
- 2022
- Engelska.
-
Ingår i: CEUR Workshop Proceedings. - 1613-0073. ; 3400, s. 120-126
- Relaterad länk:
-
https://research.cha...
Abstract
Ämnesord
Stäng
- 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.
Ämnesord
- NATURVETENSKAP -- Data- och informationsvetenskap -- Datavetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences -- Computer Sciences (hsv//eng)
Nyckelord
- Reinforcement learning
- Multi Agent Systems
- Neuro-Symbolic Systems
- Emergent Communication
Publikations- och innehållstyp
- kon (ämneskategori)
- ref (ämneskategori)
Hitta via bibliotek
Till lärosätets databas