Neural Agents Struggle to Take Turns in Bidirectional Emergent Communication - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2023

Neural Agents Struggle to Take Turns in Bidirectional Emergent Communication

Abstract

The spontaneous exchange of turns is a central aspect of human communication. Although turn-taking conventions come to us naturally, artificial dialogue agents struggle to coordinate, and must rely on hard-coded rules to engage in interactive conversations with human interlocutors. In this paper, we investigate the conditions under which artificial agents may naturally develop turn-taking conventions in a simple language game. We describe a cooperative task where success is contingent on the exchange of information along a shared communication channel where talking over each other hinders communication. Despite these environmental constraints, neural-network based agents trained to solve this task with reinforcement learning do not systematically adopt turn-taking conventions. However, we find that agents that do agree on turn-taking protocols end up performing better. Moreover, agents that are forced to perform turn-taking can learn to solve the task more quickly. This suggests that turn-taking may help to generate conversations that are easier for speakers to interpret.
Fichier principal
Vignette du fichier
2860_neural_agents_struggle_to_take.pdf (528.45 Ko) Télécharger le fichier
Origin : Publisher files allowed on an open archive

Dates and versions

hal-04264045 , version 1 (29-10-2023)

Licence

Attribution

Identifiers

  • HAL Id : hal-04264045 , version 1

Cite

Valentin Taillandier, Dieuwke Hupkes, Benoît Sagot, Emmanuel Dupoux, Paul Michel. Neural Agents Struggle to Take Turns in Bidirectional Emergent Communication. ICLR 2023 - 11th International Conference on Learning Representation, May 2023, Kigali, Rwanda. ⟨hal-04264045⟩
24 View
36 Download

Share

Gmail Facebook X LinkedIn More