| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| D4RL walker2d-medium-expert | Uni-O4 | Normalized Score5,421.3 | 90 | 14d ago | |
| D4RL walker2d-medium | IDQL | Normalized Score88.1 | 70 | 14d ago | |
| D4RL halfcheetah-medium | PRDC | Normalized Score63.5 | 70 | 19d ago | |
| D4RL halfcheetah-medium-replay | Off2On | Normalized Score0.8874 | 68 | 14d ago | |
| D4RL halfcheetah-medium-expert | MBOP | Normalized Score105.9 | 53 | 2mo ago | |
| D4RL Ant medium-offline | LoDADA | Normalized Score85.28 | 36 | 3mo ago | |
| D4RL Hopper medium-offline | LoDADA | Score40.77 | 36 | 3mo ago | |
| D4RL Walker2d medium-offline | LoDADA | Normalized Score37.45 | 36 | 3mo ago | |
| D4RL HalfCheetah medium-offline | LoDADA | Normalized Score34.97 | 36 | 3mo ago | |
| Dog & Humanoid suite | WIMLE | IQM0.897 | 32 | 3mo ago | |
| D4RL Hopper-medium | O2PPO | Normalized Score100.42 | 30 | 2mo ago | |
| D4RL MuJoCo Tasks | CPQL | Average D4RL Locomotion Score (v2)1,252.1 | 29 | 19d ago | |
| D4RL Hopper-medium-expert | TD3+BC | Normalized Score (100k Steps)112.2 | 28 | 14d ago | |
| Hopper IID (test) | RMA | Mean Episode Reward1,859 | 24 | 3mo ago | |
| Walker IID (test) | Mean Episode Reward1,909 | 24 | 3mo ago | ||
| Half Cheetah IID (test) | Mean Episode Reward2,278 | 24 | 3mo ago | ||
| Ant IID (test) | DMAP | Mean Episode Reward2,240 | 24 | 3mo ago | |
| D4RL hopper-medium-replay | COOPO | Test Return1,993.8 | 22 | 14d ago | |
| D4RL halfcheetah-medium-expert | COOPO | Test Return9,242.2 | 22 | 14d ago | |
| Hopper | DAgger | Convergence (%)100 | 20 | 3mo ago | |
| Walker2d Medium-Expert v2 | QDQ | Average Normalized Score115.9 | 19 | 19d ago | |
| Walker2d Medium-Replay v2 | CPQL | Average Normalized Score97.4 | 19 | 19d ago | |
| Walker2d Medium v2 | EDAC | Average Normalized Score92.5 | 19 | 19d ago | |
| HalfCheetah Medium-Expert v2 | EDAC | Average Normalized Score106.3 | 19 | 19d ago | |
| HalfCheetah Medium v2 | QDQ | Average Normalized Score74.1 | 19 | 19d ago |
