List your company

Offline-to-Online Reinforcement Learning on D4RL Locomotion medium

98.3Average Normalized ReturnFamO2O
66.16474.50782.8591.193Dec 11, 2025

Evaluation results

MethodLinks
FamO2OReplay Buffer Strategy=ARB2025.1298.3
FamO2OReplay Buffer Strategy=Parallel2025.1292
FamO2OReplay Buffer Strategy=BERB2025.1286.2
Cal-QLReplay Buffer Strategy=Top-N2025.1286.1
Cal-QLReplay Buffer Strategy=ARB2025.1286
Cal-QLReplay Buffer Strategy=Parallel2025.1281.7
FamO2OReplay Buffer Strategy=Top-N2025.1280.8
Cal-QLReplay Buffer Strategy=BERB2025.1280
PEXReplay Buffer Strategy=ARB2025.1275.7
PEXReplay Buffer Strategy=BERB2025.1274.6
FamO2OReplay Buffer Strategy=Naive2025.1274.5
PEXReplay Buffer Strategy=Parallel2025.1273.2
PEXReplay Buffer Strategy=Top-N2025.1272.3
Cal-QLReplay Buffer Strategy=Naive2025.1269
PEXReplay Buffer Strategy=Naive2025.1267.4