Reinforcement Learning Exploration on HWRB Atari 57 Montezuma Revenge v1
24,758ScoreGo-Explore
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Go-ExploreScale=10B2023.05 | 24,758 | 0 | |
| LBCScale=1B2023.05 | 2,500 | 0 |
Loading the SOTA2 catalog…
| Method | Links | ||
|---|---|---|---|
| Go-ExploreScale=10B2023.05 | 24,758 | 0 | |
| LBCScale=1B2023.05 | 2,500 | 0 |