Offline Reinforcement Learning on Maze2D large
96.8Normalized ReturnReal Dataset
Evaluation Results
| Method | Links | |
|---|---|---|
| Real DatasetOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=no-DP2025.12 | 96.8 | |
| Real DatasetOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=no-DP2025.12 | 89.9 | |
| Real DatasetOffline RL Algorithm=IQL, Privacy Budget (epsilon)=no-DP2025.12 | 85.9 | |
| PrivORL-nOffline RL Algorithm=IQL, Privacy Budget (epsilon)=102025.12 | 81 | |
| PrivORL-nOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=102025.12 | 80.6 | |
| PrivORL-nOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=102025.12 | 75.3 | |
| PrivORL-nOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=12025.12 | 62.4 | |
| PrivORL-nOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=12025.12 | 61.3 | |
| PrivORL-nOffline RL Algorithm=IQL, Privacy Budget (epsilon)=12025.12 | 50.3 | |
| PGMOffline RL Algorithm=IQL, Privacy Budget (epsilon)=102025.12 | 21.9 | |
| PGMOffline RL Algorithm=IQL, Privacy Budget (epsilon)=12025.12 | 16.7 | |
| PATE-GANOffline RL Algorithm=IQL, Privacy Budget (epsilon)=102025.12 | 5.9 | |
| PATE-GANOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=102025.12 | 5.8 | |
| PGMOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=102025.12 | 4 | |
| PATE-GANOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=12025.12 | 3.6 | |
| PrivSynOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=12025.12 | 3.4 | |
| PGMOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=102025.12 | 3.1 | |
| PrivSynOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=102025.12 | 2.9 | |
| PATE-GANOffline RL Algorithm=IQL, Privacy Budget (epsilon)=12025.12 | 2.9 | |
| PrivSynOffline RL Algorithm=IQL, Privacy Budget (epsilon)=102025.12 | 2.5 | |
| PGMOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=12025.12 | 1.6 | |
| PGMOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=12025.12 | 0.4 | |
| PrivSynOffline RL Algorithm=IQL, Privacy Budget (epsilon)=12025.12 | 0.4 | |
| PrePATE-GANOffline RL Algorithm=IQL, Privacy Budget (epsilon)=102025.12 | 0.4 | |
| PrePATE-GANOffline RL Algorithm=IQL, Privacy Budget (epsilon)=12025.12 | 0 | |
| PrePATE-GANOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=12025.12 | 0 | |
| PrePATE-GANOffline RL Algorithm=TD3PLUSBC, Privacy Budget (epsilon)=102025.12 | 0 | |
| PrePATE-GANOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=102025.12 | -2.4 | |
| PATE-GANOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=102025.12 | -5.2 | |
| PrePATE-GANOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=12025.12 | -6.6 | |
| PrivSynOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=12025.12 | -8.2 | |
| PrivSynOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=102025.12 | -9.9 | |
| PATE-GANOffline RL Algorithm=EDAC, Privacy Budget (epsilon)=12025.12 | -14.3 |