Projects per year
Abstract
Emergence of language grounded in perception
has been studied in computational agent societies with language games.
In this paper we introduce methods that can be used to ground
a language in the needs of the agents, i.e. practicality.
The needs of an agent arise from its goals and environment, which
together dictate what kind of a language is practical.
The methods are tested in multi-agent simulations.
Our results show that with our methods a practical language can emerge.
Interestingly we also observed, that a language does not need to be coherent
in the whole society for it to have practical benefits for the agents.
has been studied in computational agent societies with language games.
In this paper we introduce methods that can be used to ground
a language in the needs of the agents, i.e. practicality.
The needs of an agent arise from its goals and environment, which
together dictate what kind of a language is practical.
The methods are tested in multi-agent simulations.
Our results show that with our methods a practical language can emerge.
Interestingly we also observed, that a language does not need to be coherent
in the whole society for it to have practical benefits for the agents.
Original language | English |
---|---|
Title of host publication | AISB Language Learning for Artificial Agents symposium (L2A2) |
Number of pages | 5 |
Publication date | Apr 2019 |
Pages | 16-20 |
Publication status | Published - Apr 2019 |
MoE publication type | A4 Article in conference proceedings |
Event | 2019 AISB Convention - Falmouth, United Kingdom Duration: 16 Apr 2019 → 18 Apr 2019 |
Fields of Science
- 113 Computer and information sciences
- multi-agent systems
- language game
Projects
- 1 Finished
-
CACS: Cooperation-Aware Software and Creative Self-Adaptivity
Toivonen, H. T., Hadaytullah, H., Linkola, S., Hantula, O. & Männistö, T.
01/01/2018 → 31/12/2019
Project: Research project