List your company

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

107.9Average Normalized ReturnFamO2O
79.71687.03394.35101.667Dec 11, 2025

Evaluation results

MethodLinks
FamO2OReplay Buffer Strategy=ARB2025.12107.9
Cal-QLReplay Buffer Strategy=Top-N2025.12107.6
Cal-QLReplay Buffer Strategy=ARB2025.12106.9
Cal-QLReplay Buffer Strategy=BERB2025.12106.7
Cal-QLReplay Buffer Strategy=Parallel2025.12106.5
Cal-QLReplay Buffer Strategy=Naive2025.12106.1
FamO2OReplay Buffer Strategy=Parallel2025.12105.9
FamO2OReplay Buffer Strategy=BERB2025.12105.5
FamO2OReplay Buffer Strategy=Naive2025.12103.7
FamO2OReplay Buffer Strategy=Top-N2025.12100.3
PEXReplay Buffer Strategy=ARB2025.1286.2
PEXReplay Buffer Strategy=BERB2025.1283.7
PEXReplay Buffer Strategy=Top-N2025.1283.3
PEXReplay Buffer Strategy=Naive2025.1282.7
PEXReplay Buffer Strategy=Parallel2025.1280.8