SocialAI: Benchmarking Socio-Cognitive Abilities in Deep Reinforcement Learning Agents - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Preprints, Working Papers, ... Year : 2021

SocialAI: Benchmarking Socio-Cognitive Abilities in Deep Reinforcement Learning Agents

Grgur Kovač
  • Function : Author
  • PersonId : 750805
  • IdHAL : grgur-kovac
Rémy Portelas
  • Function : Author
  • PersonId : 1058561
Katja Hofmann
  • Function : Author
Pierre-Yves Oudeyer

Abstract

Building embodied autonomous agents capable of participating in social interactions with humans is one of the main challenges in AI. Within the Deep Reinforcement Learning (DRL) field, this objective motivated multiple works on embodied language use. However, current approaches focus on language as a communication tool in very simplified and non-diverse social situations: the "naturalness" of language is reduced to the concept of high vocabulary size and variability. In this paper, we argue that aiming towards human-level AI requires a broader set of key social skills: 1) language use in complex and variable social contexts; 2) beyond language, complex embodied communication in multimodal settings within constantly evolving social worlds. We explain how concepts from cognitive sciences could help AI to draw a roadmap towards human-like intelligence, with a focus on its social dimensions. As a first step, we propose to expand current research to a broader set of core social skills. To do this, we present SocialAI, a benchmark to assess the acquisition of social skills of DRL agents using multiple grid-world environments featuring other (scripted) social agents. We then study the limits of a recent SOTA DRL approach when tested on SocialAI and discuss important next steps towards proficient social agents. Videos and code are available at https://sites.google.com/view/socialai.
Fichier principal
Vignette du fichier
socialAI-paper.pdf (1.26 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03372670 , version 1 (11-10-2021)

Identifiers

  • HAL Id : hal-03372670 , version 1

Cite

Grgur Kovač, Rémy Portelas, Katja Hofmann, Pierre-Yves Oudeyer. SocialAI: Benchmarking Socio-Cognitive Abilities in Deep Reinforcement Learning Agents. 2021. ⟨hal-03372670⟩

Collections

INRIA INRIA2 GENCI
47 View
146 Download

Share

Gmail Mastodon Facebook X LinkedIn More