| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| D4RL walker2d-medium-expert | O2PPO | Normalized Score121.4 | 47 | 4d ago | |
| D4RL walker2d-medium | IDQL | Normalized Score88.1 | 44 | 4d ago | |
| D4RL halfcheetah-medium | PRDC | Normalized Score63.5 | 44 | 4d ago | |
| D4RL halfcheetah-medium-expert | O2SAC | Normalized Score100.41 | 37 | 4d ago | |
| D4RL Ant medium-offline | LoDADA | Normalized Score85.28 | 36 | 4d ago | |
| D4RL Hopper medium-offline | LoDADA | Score40.77 | 36 | 4d ago | |
| D4RL Walker2d medium-offline | LoDADA | Normalized Score37.45 | 36 | 4d ago | |
| D4RL HalfCheetah medium-offline | LoDADA | Normalized Score34.97 | 36 | 4d ago | |
| D4RL halfcheetah-medium-replay | Off2On | Normalized Score0.8874 | 33 | 4d ago | |
| Dog & Humanoid suite | WIMLE | IQM0.897 | 32 | 4d ago | |
| Hopper IID (test) | RMA | Mean Episode Reward1,859 | 24 | 4d ago | |
| Walker IID (test) | Mean Episode Reward1,909 | 24 | 4d ago | ||
| Half Cheetah IID (test) | Mean Episode Reward2,278 | 24 | 4d ago | ||
| Ant IID (test) | DMAP | Mean Episode Reward2,240 | 24 | 4d ago | |
| Hopper | DAgger | Convergence (%)100 | 20 | 4d ago | |
| D4RL Hopper-medium-expert | TD3+BC | Normalized Score (100k Steps)112.2 | 18 | 4d ago | |
| D4RL Hopper-medium | O2PPO | Normalized Score100.42 | 14 | 4d ago | |
| NeoRL Walker2d Medium | VIPO | Mean Normalized Score76.8 | 12 | 4d ago | |
| NeoRL Hopper Medium | LEQ | Mean Normalized Score104.3 | 12 | 4d ago | |
| NeoRL HalfCheetah-Medium | NEUBAY | Mean Normalized Score81.1 | 12 | 4d ago | |
| NeoRL Walker2d Low | VIPO | Mean Normalized Score67.6 | 12 | 4d ago | |
| NeoRL Hopper-Low | VIPO | Mean Normalized Score30.7 | 12 | 4d ago | |
| NeoRL HalfCheetah Low | VIPO | Mean Normalized Score58.5 | 12 | 4d ago | |
| D4RL Gym Aggregate | A2PO | Gym Total1,563.3 | 12 | 4d ago | |
| D4RL Gym random-medium-expert | A2PO | HalfCheetah Return90.6 | 12 | 4d ago |
