Offline Imitation Learning on D4RL Ant v2 (expert)
126.4Normalized ScoreCEIL
Evaluation Results
| Method | Links | |
|---|---|---|
| CEILProtocol=S-off-LfO, Trials=302023.06 | 126.4 | |
| CEILProtocol=C-off-LfO, Trials=302023.06 | 125.2 | |
| DemoDICEProtocol=C-off-LfD, Trials=302023.06 | 122.5 | |
| SMODICEProtocol=S-off-LfD, Trials=302023.06 | 122 | |
| SMODICEProtocol=S-off-LfO, Trials=302023.06 | 122 | |
| SMODICEProtocol=C-off-LfD, Trials=302023.06 | 120.9 | |
| CEILProtocol=S-off-LfD, Trials=302023.06 | 117.8 | |
| SMODICEProtocol=C-off-LfO, Trials=302023.06 | 117.7 | |
| DemoDICEProtocol=S-off-LfD, Trials=302023.06 | 114.2 | |
| CEILProtocol=C-off-LfD, Trials=302023.06 | 112.2 | |
| ValueDICEProtocol=S-off-LfD, Trials=302023.06 | 90.5 | |
| IQ-LearnProtocol=S-off-LfD, Trials=302023.06 | 85.9 | |
| ORIL (TD3+BC)Protocol=S-off-LfD, Trials=302023.06 | 76.8 | |
| IQ-LearnProtocol=C-off-LfD, Trials=302023.06 | 55.8 | |
| SQIL (TD3+BC)Protocol=S-off-LfD, Trials=302023.06 | 44.3 | |
| ORIL (TD3+BC)Protocol=S-off-LfO, Trials=302023.06 | 44.3 | |
| ORIL (TD3+BC)Protocol=C-off-LfD, Trials=302023.06 | 32.1 | |
| ORIL (TD3+BC)Protocol=C-off-LfO, Trials=302023.06 | 28.2 | |
| ValueDICEProtocol=C-off-LfD, Trials=302023.06 | 22.3 | |
| SQIL (TD3+BC)Protocol=C-off-LfD, Trials=302023.06 | 21.2 |