Offline Reinforcement Learning on V-D4RL Walker-walk medium-replay
56.6Normalized ReturnOffline DV2
Evaluation results
| Method | Links | |
|---|---|---|
| Offline DV2Implementation Source=Original Paper Results [20]2024.11 | 56.6 | |
| Offline DV2Implementation Source=This Paper Re-implementation2024.11 | 42.5 | |
| LOMPOImplementation Source=Original Paper Results [20]2024.11 | 34.7 | |
| C-LAPImplementation Source=This Paper2024.11 | 34.5 | |
| LOMPOImplementation Source=This Paper Re-implementation2024.11 | 11.4 |