Reinforcement Learning on Procgen 16 environments
89.4BigFish ScoreLAOM
Evaluation results
| Method | Links | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| LAOMMode=Fine-tuned2026.06 | 89.4 | 45.8 | 16.8 | 19.8 | 17.6 | 93.4 | 35 | 39.2 | 83.4 | 66.4 | 70.4 | 98.4 | 36.4 | 75 | 8.6 | 75 | 54.4 | |
| LAFPMode=Frozen2026.06 | 88.8 | 55 | 27.8 | 29.6 | 29 | 96.4 | 28.2 | 35.6 | 97.2 | 79.4 | 73 | 99.8 | 87 | 92.4 | 8 | 73.6 | 62.6 | |
| LAOMMode=Frozen2026.06 | 88 | 50.4 | 19.4 | 8.8 | 20.4 | 94 | 29.6 | 42.6 | 83.2 | 69.6 | 71.2 | 98 | 31.8 | 73.2 | 5.8 | 76.2 | 53.9 | |
| LAFPMode=Fine-tuned2026.06 | 82.4 | 34.2 | 2.2 | 27 | 24 | 94.4 | 0 | 33 | 93.4 | 81.6 | 62.2 | 93 | 84.8 | 88.4 | 9.4 | 0 | 50.6 |