AI Paper Atlas

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

A mathematical theory of cooperative communication

Pei Wang, Junqi Wang, Pushpi Paranamana, Patrick Shafto

NeurIPS 2020 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Emergent communication in referential games · 20 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 full Sinkhorn scaling instead of one-step approximationcooperative communication plans · Numeral interpretationCooperative Index: 0.5 -> 1Improved
use full Sinkhorn scaling instead of one-step approximation under common-ground perturbationEOT plans · Dirichlet simulations, 100x100Cooperative IndexImproved
increase greediness lambda above 1 (ablation)EOT plans · Perturbed 3x3 exampleCooperative Index: 0.41 -> 0.25Hurt
increase lambda from 0.1 to 40 (ablation)EOT plans · 50x50 perturbed matricesCooperative Index gap vs unperturbedHurt
add linear approximation correction for perturbed MSK plan re-estimation · Perturbed M, L1 errorL1 distanceImproved

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