List your company

Offline-to-Online Reinforcement Learning on D4RL Locomotion medium-replay

90.8Avg Normalized ReturnFamO2O
56.58465.46774.3583.233Dec 11, 2025

Evaluation results

MethodLinks
FamO2OReplay Buffer Strategy=ARB2025.1290.8
FamO2OReplay Buffer Strategy=BERB2025.1286.2
Cal-QLReplay Buffer Strategy=ARB2025.1286
FamO2OReplay Buffer Strategy=Naive2025.1286
Cal-QLReplay Buffer Strategy=Top-N2025.1284.5
FamO2OReplay Buffer Strategy=Parallel2025.1284.5
Cal-QLReplay Buffer Strategy=BERB2025.1283
Cal-QLReplay Buffer Strategy=Parallel2025.1282.9
PEXReplay Buffer Strategy=ARB2025.1282.9
Cal-QLReplay Buffer Strategy=Naive2025.1281.9
FamO2OReplay Buffer Strategy=Top-N2025.1281.5
PEXReplay Buffer Strategy=Top-N2025.1276.2
PEXReplay Buffer Strategy=BERB2025.1261.7
PEXReplay Buffer Strategy=Naive2025.1258.4
PEXReplay Buffer Strategy=Parallel2025.1257.9