List your company

Continuous Control on MuJoCo v5 Suite

4,828Ant-v5REDQ
-192.081,111.212,414.53,717.79Jul 31, 2025Aug 31, 2025Oct 2, 2025Nov 3, 2025Dec 4, 2025Jan 5, 2026Feb 6, 2026

Evaluation results

MethodLinks
REDQEnsemble size=10, Update-to-Data Ratio=20, Interaction budget=300,000, Evaluation Metric=InterQuantile Mean (IQM)2025.074,8288,6783,4155,404—4,749—
AEAEnsemble size=10, Update-to-Data Ratio=20, Interaction budget=300,000, Evaluation Metric=InterQuantile Mean (IQM)2025.074,7449,6613,5555,376—4,652—
PPOseeds=9 (0-8)2026.021,470.83,451.3617.5147.5977.41,765.41,405
BPPOseeds=9 (0-8)2026.021,293.93,856.31,321.61,099.29972,697.31,877.5
BTRPOseeds=9 (0-8)2026.021,169.13,299.2928.9110.2979.61,3971,314
TRPOseeds=9 (0-8)2026.02816.72,819.2913.2204.9992.81,076.71,137.2
DRNDEnsemble size=2, Update-to-Data Ratio=20, Interaction budget=300,000, Evaluation Metric=InterQuantile Mean (IQM)2025.077977,8923,0152,853—5,054—
DSACEnsemble size=2, Update-to-Data Ratio=20, Interaction budget=300,000, Evaluation Metric=InterQuantile Mean (IQM)2025.077769,0592,640908—5,362—
SAC-NEnsemble size=10, Update-to-Data Ratio=20, Interaction budget=300,000, Evaluation Metric=InterQuantile Mean (IQM)2025.0715,4252,0635,341—1,035—