| Dataset Name | SOTA Method | Metric | Trend | ||
|---|---|---|---|---|---|
| OpenAI Gym MuJoCo Normalized v4 | NC-LQL | Normalized Mean Return95.5 | 50 | 3mo ago | |
| Antmaze large-diverse | RLPD | Score93.5 | 8 | 3mo ago | |
| Antmaze large-play | RLPD | Score94.8 | 8 | 3mo ago | |
| Antmaze medium-diverse | RLPD | Score98.5 | 8 | 3mo ago | |
| Antmaze medium-play | RLPD | Score98.7 | 8 | 3mo ago | |
| Antmaze umaze-diverse | BC-PEX | Score99.9 | 8 | 3mo ago | |
| Antmaze umaze | RLPD | Score99.9 | 8 | 3mo ago | |
| MinAtar (|A|=216, k=3) Macro-Action (online) | Breakout Score11.98 | 5 | 21d ago | ||
| WalkerWalk DMControl (final) | GoRL(FM) | Normalized Return919.61 | 5 | 3mo ago | |
| HopperStand DMControl (final) | GoRL(Diff) | Normalized Return874.63 | 5 | 3mo ago | |
| FishSwim DMControl (final) | GoRL(FM) | Normalized Return641.01 | 5 | 3mo ago | |
| FingerTurnHard DMControl (final) | GoRL(Diff) | Normalized Return884.59 | 5 | 3mo ago | |
| DMControl FingerSpin (final) | GoRL(FM) | Normalized Return903.92 | 5 | 3mo ago | |
| CheetahRun DMControl (final) | GoRL(Diff) | Normalized Return902.24 | 5 | 3mo ago |
