List your company

Offline Reinforcement Learning on Minari Simple

69.1Humanoid ScoreO2O
61.8263.7165.667.49May 7, 2026

Evaluation results

MethodLinks
O2ONumber of seeds=102026.0569.114.813.185.14.437.3
RLPDNumber of seeds=102026.0565.38854.573.964.669.3
SACfDNumber of seeds=102026.056484.255.562.65564.3
SPEQNumber of seeds=102026.0562.384.45464.25463.8
SOPENumber of seeds=102026.0562.197.760.765.163.569.8