Research in multi-agent cooperation has shown that artificial agents are able to learn to play a simple referential game while developing a shared lexicon. This lexicon is not easy to analyze, as it does not show many properties of a natural language. In a simple referential game with two neural network-based agents, we analyze the object-symbol mapping trying to understand what kind of strategy was used to develop the emergent language. We see that, when the environment is uniformly distributed, the agents rely on a random subset of features to describe the objects. When we modify the objects making one feature non-uniformly distributed,the agents realize it is less informative and start to ignore it, and, surprisingly, they make a better use of the remaining features. This interesting result suggests that more natural, less uniformly distributed environments might aid in spurring the emergence of better-behaved languages.

Focus on what’s informative and ignore what’s not: Communication strategies in a referential game / Dessì, Roberto; Bouchacourt, Diane; Crepaldi, Davide; Baroni, Marco. - (2019). ((Intervento presentato al convegno 3rd Conference on Neural Information Processing Systems (NeurIPS 2019), Vancouver, Canada.

Focus on what’s informative and ignore what’s not: Communication strategies in a referential game

Dessì, Roberto;Crepaldi, Davide;
2019

Abstract

Research in multi-agent cooperation has shown that artificial agents are able to learn to play a simple referential game while developing a shared lexicon. This lexicon is not easy to analyze, as it does not show many properties of a natural language. In a simple referential game with two neural network-based agents, we analyze the object-symbol mapping trying to understand what kind of strategy was used to develop the emergent language. We see that, when the environment is uniformly distributed, the agents rely on a random subset of features to describe the objects. When we modify the objects making one feature non-uniformly distributed,the agents realize it is less informative and start to ignore it, and, surprisingly, they make a better use of the remaining features. This interesting result suggests that more natural, less uniformly distributed environments might aid in spurring the emergence of better-behaved languages.
Advances in neural information processing systems: 33rd Conference on Neural Information Processing Systems (neurips 2019)
1713807939
9781713807933
https://arxiv.org/abs/1911.01892
Neural Info Process Sys
Dessì, Roberto; Bouchacourt, Diane; Crepaldi, Davide; Baroni, Marco
File in questo prodotto:
File Dimensione Formato  
Dessì2019.pdf

accesso aperto

Tipologia: Documento in Post-print
Licenza: Non specificato
Dimensione 79.27 kB
Formato Adobe PDF
79.27 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/20.500.11767/110842
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus ND
  • ???jsp.display-item.citation.isi??? ND
social impact