Offline Reinforcement Learning on D4RL Hopper-M
69Normalized ReturnDAWM-TD3BC
Evaluation Results
| Method | Links | |
|---|---|---|
| DAWM-TD3BCModel Framework=DAWM, RL Algorithm=TD3BC2025.09 | 69 | |
| DWM-TD3BCModel Framework=DWM, RL Algorithm=TD3BC2025.09 | 65 | |
| DAWM-IQLModel Framework=DAWM, RL Algorithm=IQL2025.09 | 64 | |
| DWM-IQLModel Framework=DWM, RL Algorithm=IQL2025.09 | 54 | |
| DDModel Framework=DD2025.09 | 49 | |
| DAWM-TD3BCAgent=TD3BC, Training Strategy=DAWM-synthetic2025.09 | 0.69 | |
| SSORL-IQLAgent=IQL, Training Strategy=SSORL-augmented2025.09 | 0.69 | |
| SSORL-TD3BCAgent=TD3BC, Training Strategy=SSORL-augmented2025.09 | 0.64 | |
| DAWM-IQLAgent=IQL, Training Strategy=DAWM-synthetic2025.09 | 0.64 | |
| IQLAgent=IQL, Training Strategy=Standard (Real Data)2025.09 | 0.61 | |
| TD3BCAgent=TD3BC, Training Strategy=Standard (Real Data)2025.09 | 0.58 |