List your company
ResearchFormerly WizWand

Offline Reinforcement Learning on walker2d Mixed Dataset

64.4Normalized RewardMOPO
-2.6814.73532.1549.565Jun 6, 2024
Updated 8mo ago

Evaluation results

MethodLinks
MOPODataset Ratio (%)=50, Dataset Type=random-medium2024.0664.458.9
MOPODataset Ratio (%)=10, Dataset Type=random-medium2024.0644.524.5
MOBILEDataset Ratio (%)=50, Dataset Type=random-medium2024.0636.129.6
MOMBODataset Ratio (%)=5, Dataset Type=random-expert2024.062418.4
MOMBODataset Ratio (%)=1, Dataset Type=random-medium2024.062218.7
MOMBODataset Ratio (%)=1, Dataset Type=random-expert2024.0621.818.2
MOMBODataset Ratio (%)=5, Dataset Type=random-medium2024.0621.718.5
MOBILEDataset Ratio (%)=1, Dataset Type=random-expert2024.0621.616.6
MOMBODataset Ratio (%)=10, Dataset Type=random-expert2024.0621.317.2
MOMBODataset Ratio (%)=10, Dataset Type=random-medium2024.0617.816.8
MOMBODataset Ratio (%)=50, Dataset Type=random-expert2024.0616.411.8
MOPODataset Ratio (%)=50, Dataset Type=random-expert2024.06167.7
MOBILEDataset Ratio (%)=1, Dataset Type=random-medium2024.0615.913.1
MOBILEDataset Ratio (%)=50, Dataset Type=random-expert2024.0615.79.8
MOBILEDataset Ratio (%)=10, Dataset Type=random-expert2024.0614.914
MOMBODataset Ratio (%)=50, Dataset Type=random-medium2024.0614.737.7
MOBILEDataset Ratio (%)=5, Dataset Type=random-expert2024.0613.813.3
MOBILEDataset Ratio (%)=10, Dataset Type=random-medium2024.0611.110.9
MOBILEDataset Ratio (%)=5, Dataset Type=random-medium2024.0610.610.3
MOPODataset Ratio (%)=5, Dataset Type=random-medium2024.065.24.7
MOPODataset Ratio (%)=10, Dataset Type=random-expert2024.064.22.9
MOPODataset Ratio (%)=5, Dataset Type=random-expert2024.061.62
MOPODataset Ratio (%)=1, Dataset Type=random-medium2024.060.10.1
MOPODataset Ratio (%)=1, Dataset Type=random-expert2024.06-0.10.3