List your company

Bosslevel on BabyAI

0.343Average Pass RatePolychromic PPO
0.220280.252140.2840.31586Sep 29, 2025

Evaluation results

MethodLinks
Polychromic PPOevaluation_protocol=pass@1, initial-state perturbations=large2025.090.343
Poly-PPO w/ UCBevaluation_protocol=pass@1, initial-state perturbations=large2025.090.328
PPO w/ UCBevaluation_protocol=pass@1, initial-state perturbations=large2025.090.282
REINFORCE w/ UCBevaluation_protocol=pass@1, initial-state perturbations=large2025.090.276
PPOevaluation_protocol=pass@1, initial-state perturbations=large2025.090.266
Pretrained policyevaluation_protocol=pass@1, initial-state perturbations=large2025.090.238
REINFORCE w/ Baselineevaluation_protocol=pass@1, initial-state perturbations=large2025.090.225