English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Building embodied autonomous agents capable of participating in socialinteractions with humans is one of the main challenges in AI. This problemmotivated many research directions on embodied language use. Current approachesfocus on language as a communication tool in very simplified and non diversesocial situations: the "naturalness" of language is reduced to the concept ofhigh vocabulary size and variability. In this paper, we argue that aimingtowards human-level AI requires a broader set of key social skills: 1) languageuse in complex and variable social contexts; 2) beyond language, complexembodied communication in multimodal settings within constantly evolving socialworlds. In this work we explain how concepts from cognitive sciences could helpAI to draw a roadmap towards human-like intelligence, with a focus on itssocial dimensions. We then study the limits of a recent SOTA Deep RL approachwhen tested on a first grid-world environment from the upcoming SocialAI, abenchmark to assess the social skills of Deep RL agents. Videos and code areavailable at https://sites.google.com/view/socialai01 .

SocialAI 0.1: Towards a Benchmark to Stimulate Research on Socio-Cognitive Abilities in Deep Reinforcement Learning Agents