Offline Reinforcement Learning on medical dataset
0.757ReturnGORMPO NeuralODE
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| GORMPO NeuralODEseeds=5, episodes=10002026.05 | 0.757 | 0.036 | 0.322 | |
| GORMPO RealNVPseeds=5, episodes=10002026.05 | 0.739 | 0.222 | 1.861 | |
| MBPOseeds=5, episodes=10002026.05 | 0.644 | 0.116 | 0.616 | |
| MOBILEseeds=5, episodes=10002026.05 | 0.637 | 0.44 | 3.479 | |
| GORMPO KDEseeds=5, episodes=10002026.05 | 0.586 | 0.215 | 1.194 | |
| GORMPO DDPMseeds=5, episodes=10002026.05 | 0.561 | 0.145 | 0.434 | |
| SPOTseeds=5, episodes=10002026.05 | 0.419 | 0.196 | 0.036 | |
| GORMPO VAEseeds=5, episodes=10002026.05 | 0.377 | 0.216 | 0.334 |