AI Paper Atlas

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

Learning to Cooperate with Minimal Observability

Chin-wing Leung, Paolo Turrini, Fernando P. Santos, Mirco Musolesi

AAAI 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Intrinsically motivated exploration · 2 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
add mutual partner-selection update (selected agent also learns) (ablation)Local Information Model · Prisoner's Dilemma, 30 agentsmutual cooperation (%): below 20% -> above 40%Improved
add global information with probability pG (ablation)Local Information Model · Prisoner's Dilemmamutual cooperation (%): stabilises around 85% at pG = 0.3Improved
add one random third-party observer per gameplayLocal Information Model · Prisoner's Dilemma, 30 agentsmutual cooperation (%): over 90% of interactions mutual cooperationImproved
add one observer per gameplayLocal Information Model · Prisoner's Dilemma, 30 agentsdistinct partners selected per agent: 1.5 -> 4.26Improved
increase population size to 50 (ablation)Observer Model · Prisoner's Dilemma, 50 agentsmutual cooperation (%): drops to about 85%Hurt
increase observers from 1 to 2 (ablation)Observer Model · Prisoner's Dilemma, 50 agentsmutual cooperation (%): 85% -> above 90%Improved
lower exploration rate (0.005) (ablation)Observer Model · Prisoner's Dilemma, 30 agentsconvergence speed: cooperation starts to grow at 25,000 instead of 12,500Hurt
raise learning and exploration rates (ablation)Observer Model · Prisoner's Dilemma, 30 agentsmutual cooperation (%): faster convergence, but cooperation kept below 80%Mixed

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