| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| D4RL Antmaze | ROAD | Success Rate (Large Diverse)74.51 | 20 | 19d ago | |
| D4RL 6 environments min-max normalized (averaged) | SMAC | Normalized Regret0.031 | 16 | 3mo ago | |
| D4RL Antmaze | PEX | Avg Normalized Return91 | 15 | 3mo ago | |
| D4RL Locomotion medium-expert | FamO2O | Average Normalized Return107.9 | 15 | 3mo ago | |
| D4RL Locomotion medium | FamO2O | Average Normalized Return98.3 | 15 | 3mo ago | |
| D4RL Locomotion medium-replay | FamO2O | Avg Normalized Return90.8 | 15 | 3mo ago | |
| D4RL Locomotion random | FamO2O | Avg Normalized Return53.1 | 15 | 3mo ago | |
| D4RL Franka Kitchen | ROAD | Partial Success Rate46.65 | 12 | 19d ago | |
| relocate | SMAC | Regret62.8 | 12 | 3mo ago | |
| pen | SMAC | Regret5.3 | 12 | 3mo ago | |
| door | SMAC | Regret50.3 | 12 | 3mo ago | |
| D4RL Aggregate | ROAD | Average Normalized Score71.95 | 10 | 19d ago | |
| D4RL Gym-Locomotion | ROAD | HalfCheetah Return (Random)88.36 | 10 | 19d ago | |
| MinAtar | DRIFT | Breakout Score (Online)17.1 | 10 | 21d ago | |
| D4RL Cheetah expert discretized | DRIFT | Online Normalized Score9.7 | 9 | 21d ago | |
| D4RL Cheetah medium discretized | Online Score16.9 | 9 | 21d ago | ||
| D4RL Walker expert discretized | DRIFT | Online Normalized Score14.8 | 9 | 21d ago | |
| D4RL Walker medium discretized | DRIFT | Online Normalised Score15.9 | 9 | 21d ago | |
| D4RL Hopper expert discretized | DRIFT | Online Normalised Score47.1 | 9 | 21d ago | |
| D4RL Hopper medium discretized | DRIFT | Online Normalized Score47.9 | 9 | 21d ago | |
| D4RL antmaze-medium-diverse | Cal-QL | OSR81.7 | 9 | 21d ago | |
| D4RL antmaze-medium-play | CQL | OSR81.7 | 9 | 21d ago | |
| Adroit Average | DUAL | Average Online Return46.71 | 8 | 2d ago | |
| relocate cloned v1 | DUAL | Average Online Expected Return0.44 | 8 | 2d ago | |
| hammer-cloned v1 | DUAL | Average Online Expected Return46.74 | 8 | 2d ago |
