List your company

Offline-to-Online Reinforcement Learning on D4RL Locomotion (random)

53.1Avg Normalized ReturnFamO2O
8.920.37531.8543.325Dec 11, 2025

Evaluation results

MethodLinks
FamO2OReplay Buffer Strategy=ARB2025.1253.1
FamO2OReplay Buffer Strategy=Parallel2025.1240.9
FamO2OReplay Buffer Strategy=BERB2025.1235.9
FamO2OReplay Buffer Strategy=Naive2025.1230.5
FamO2OReplay Buffer Strategy=Top-N2025.1226.3
PEXReplay Buffer Strategy=ARB2025.1224.9
Cal-QLReplay Buffer Strategy=ARB2025.1217.9
PEXReplay Buffer Strategy=Naive2025.1215.4
PEXReplay Buffer Strategy=Parallel2025.1215.3
PEXReplay Buffer Strategy=BERB2025.1214.9
PEXReplay Buffer Strategy=Top-N2025.1213.4
Cal-QLReplay Buffer Strategy=Parallel2025.1211.6
Cal-QLReplay Buffer Strategy=BERB2025.1211.2
Cal-QLReplay Buffer Strategy=Top-N2025.1210.9
Cal-QLReplay Buffer Strategy=Naive2025.1210.6