Offline-to-online Reinforcement Learning on MinAtar
17.1Breakout Score (Online)
DRIFT
Updated 21d ago
Evaluation Results
| Method | Links | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
2026.05 | 17.1 | 0.43 | 0.5 | 1.17 | 1.26 | 25 | 0.15 | 1.84 | 2.23 | 42.64 | 0.91 | 17.55 | |
2026.05 | 17.01 | 0.01 | 0.66 | 1.13 | 2.54 | 23.56 | 0.12 | 0.9 | 0 | 41.6 | 0.67 | 16.84 | |
2026.05 | 16.73 | 0.32 | 0.53 | 1.05 | 1.89 | 22.98 | 0.37 | 1 | 0 | 48.58 | 0.62 | 18.07 | |
2026.05 | 14.69 | 0.62 | 0.58 | 1.15 | 22.97 | 26.5 | 0.42 | 0.95 | 0 | 52.56 | 4.92 | 19.17 | |
2026.05 | 14.61 | 1.19 | 0.67 | 1.04 | 19.89 | 25.71 | 0.46 | 0.86 | 0.27 | 54.09 | 4.5 | 19.26 | |
2026.05 | 14.25 | 0.38 | 0.55 | 1.06 | 2.99 | 25.38 | 0.24 | 0.89 | 0 | 49.04 | 0.83 | 18.12 | |
2026.05 | 12.48 | 0.29 | 0.55 | 0.91 | 0.31 | 24.57 | 0.38 | 0.58 | 0.19 | 35.52 | 0.34 | 14.81 | |
2026.05 | 0.52 | - | - | 0.5 | - | 0.13 | - | 0.13 | - | 2.96 | - | 0.85 | |
2026.05 | 0.51 | 0.5 | 0.38 | 0.53 | 15.85 | 15.69 | 0.28 | 0.2 | 4.52 | 4.52 | 4.31 | 4.29 | |
2026.05 | 0.24 | 0.19 | 0.44 | 0.53 | 0.95 | 0.76 | 0.33 | 0.35 | 0 | 0 | 0.38 | 0.38 |