AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Intra-agent speech permits zero-shot task acquisition

Chen Yan, Federico Carnevale, Petko Georgiev, Adam Santoro, Aurelia Guy, Alistair Muldal, Chia-Chun Hung, Josh S Abramson, Timothy P Lillicrap, Greg Wayne

NeurIPS 2022 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Embodied agent learning · 3 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use semi-supervised captioning instead of supervised, on novel drum object with 585 labeled samplescaptioning model · Drum captioningtrue positive rate: 20\% -> 70\%Improved
add unpaired images via semi-supervised methodscaptioning model · Playhouse captioninglog probability, CIDEr, color-object accuracy: equivalent to 3$\times$ more labeled dataImproved
add caption loss and caption-matching loss to behavioral cloning without drum interaction dataagent · lift drum and ask color drumnormalized reward: approximately $70\%$ of the performanceImproved
reduce labeled drum captions from 585 to 150 (ablation)agent · drum color QA and lift drumnormalized reward: 585 -> 150 captionsNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy