Reinforcement Learning on Acrobot v1
-140.16Mean Return
GB-DQN
Updated 1mo ago
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
2025.12 | -140.16 | 88.52 | - | |
2026.02 | -147.16 | 71.06 | - | |
2025.12 | -149.59 | 85.72 | - | |
2025.12 | -154.82 | 85.56 | - | |
2026.02 | -156.9 | 82.4 | - | |
2026.02 | -164.69 | 84.03 | - | |
2025.12 | -166.32 | 97.39 | - | |
2026.02 | -172.6 | 106.6 | - | |
2025.12 | -264.58 | 130.77 | - | |
2026.02 | -498 | 19.9 | - | |
2025.12 | -5,000 | - | 0 | |
2025.12 | -7,518 | - | 85 | |
2025.12 | -7,715 | - | 90 | |
2025.12 | -8,013 | - | 95 |