List your company

Offline-to-Online Reinforcement Learning on D4RL Antmaze

91Avg Normalized ReturnPEX
55.1264.43573.7583.065Dec 11, 2025

Evaluation results

MethodLinks
PEXReplay Buffer Strategy=ARB2025.1291
FamO2OReplay Buffer Strategy=ARB2025.1288.4
PEXReplay Buffer Strategy=Parallel2025.1287.4
PEXReplay Buffer Strategy=Top-N2025.1287.1
PEXReplay Buffer Strategy=BERB2025.1286.5
FamO2OReplay Buffer Strategy=Parallel2025.1285.8
Cal-QLReplay Buffer Strategy=ARB2025.1285.2
PEXReplay Buffer Strategy=Naive2025.1283.4
FamO2OReplay Buffer Strategy=BERB2025.1283.3
FamO2OReplay Buffer Strategy=Top-N2025.1283.2
Cal-QLReplay Buffer Strategy=Parallel2025.1281.3
Cal-QLReplay Buffer Strategy=Naive2025.1276.6
FamO2OReplay Buffer Strategy=Naive2025.1275.8
Cal-QLReplay Buffer Strategy=BERB2025.1275.3
Cal-QLReplay Buffer Strategy=Top-N2025.1256.5