Autotelic Principle : the role of intrinsic motivation in the emergence and development of artificial language

Abstract : This thesis studies the role of intrinsic motivation in the emergence and development of communicative systems in populations of artificial agents. To be more specific, our goal is to explore how populations of agents can use a particular motivation system called autotelic principle to regulate their language development and the resulting dynamics at the population level.To achieve this, we first propose a concrete implementation of the autotelic principle. The core of this system is based on the balance between challenges, tasks to be done to achieve a goal, and skills, the abilities the system can employ to accomplish the different tasks. The relation between the two elements is not steady but regularly becomes destabilised when new skills are learned, which allows the system to attempt challenges of increasing complexity. Then, we test the usefulness of the autotelic principle in a series of language evolution experiments. In the first set of experiments, a population of artificial agents should develop a language to refer to objects with discrete values. These experiments focus on how unambiguous communicative systems can emerge when the autotelic principle is employed to scaffold language development into stages of increasing difficulty. In the second set of experiments, agents should agree on a language to communicate with about colour samples. In this part, we explore how the motivation system can regulate the linguistic complexity of interactions for a continuous domain and examine the value of the autotelic principle as a mechanism to control several language strategies simultaneously. To summarise, we have shown through our work that the autotelic principle can be used as a general mechanism to regulate complexity in language emergence in an autonomous way for discrete and continuous domains.
Complete list of metadatas

https://tel.archives-ouvertes.fr/tel-01765234
Contributor : Abes Star <>
Submitted on : Thursday, March 7, 2019 - 4:56:06 PM
Last modification on : Thursday, April 4, 2019 - 1:24:47 AM

File

Cornudella_Gaya-2017-These.pdf
Version validated by the jury (STAR)

Identifiers

  • HAL Id : tel-01765234, version 2

Collections

Citation

Miquel Cornudella Gaya. Autotelic Principle : the role of intrinsic motivation in the emergence and development of artificial language. Artificial Intelligence [cs.AI]. PSL Research University, 2017. English. ⟨NNT : 2017PSLEE082⟩. ⟨tel-01765234v2⟩

Share

Metrics

Record views

90

Files downloads

38