AI Paper Atlas

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

Modeling Conceptual Understanding in Image Reference Games

Rodolfo Corona Rodriguez, Stephan Alaniz, Zeynep Akata

NeurIPS 2019 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Theory-of-mind social reasoning · 24 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 Epsilon Greedy attribute selection during practice instead of the Reactive policyspeaker · AwA2, SUN Attribute, and CUB test setsaverage rewardImproved
use Active attribute selection during practice instead of the Reactive policyspeaker · AwA2, SUN Attribute, and CUB test setsaverage rewardImproved
direct practice-game queries toward identifying misunderstood attributesEpsilon Greedy and Active speakers · image reference game; first 20 practice gamespractice games needed to identify misunderstood attributes: at least five times fasterImproved
add an agent embedding to the attribute-selection input (ablation)Epsilon Greedy speaker · AwA2, SUN Attribute, and CUB; ALE and PNAS perception modulesaverage rewardImproved
use Epsilon Greedy or Active selection rather than Random Sampling during practicespeaker agent embeddings · listener-cluster recoveryvariation of informationImproved
use a learned policy rather than random cluster assignmentspeaker agent embeddings · listener-cluster recoveryvariation of informationImproved
use Active selection instead of Epsilon Greedy selectionspeaker · listener-cluster recoveryvariation of informationNo clear effect
use different perceptual modules for speaker and listenersEpsilon Greedy speaker (ALE) and listener population (PNAS) · image reference game, including AwA2average rewardHurt
use Epsilon Greedy selection rather than random attribute selectionspeaker with ALE perception and listeners with PNAS perception · image reference gameaverage rewardImproved

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