List your company

Human-AI Collaboration on Overcooked-AI (Evaluation partner population (novel AI behaviors))

165.8Cramped Room ScorePASD
28.5264.1699.8135.44May 23, 2026

Evaluation results

MethodLinks
PASDPartner versions=Early, intermediate, and final checkpoints, Starting positions=Both2026.05165.8145.8101.357.3746.87
FCPPartner versions=Early, intermediate, and final checkpoints, Starting positions=Both2026.05137.790.683.951.336.7
HiPTPartner versions=Early, intermediate, and final checkpoints, Starting positions=Both2026.05117.986.29638.135.6
DIAYNPartner versions=Early, intermediate, and final checkpoints, Starting positions=Both2026.0533.81.522.51.21.3