Offline Reinforcement Learning on HalfCheetah Expert
1,002.09Episodic Return
BCQ
Updated 1mo ago
Evaluation Results
| Method | Links | ||
|---|---|---|---|
2026.02 | 1,002.09 | - | |
2026.02 | 29.14 | - | |
2026.02 | 10.33 | - | |
2026.02 | 2.49 | - | |
2026.02 | 1.26 | - | |
2026.02 | -0.31 | - | |
2026.02 | -0.71 | - | |
2026.02 | -1.19 | - | |
2026.02 | -123.18 | - | |
2026.02 | -319.23 | - | |
2026.02 | -367.81 | - | |
2026.02 | -428.26 | - | |
2025.12 | - | 4.9 | |
2025.12 | - | 3.6 | |
2025.12 | - | 2.9 | |
2025.12 | - | 6.2 | |
2025.12 | - | 5.9 | |
2025.12 | - | 10.7 | |
2025.12 | - | 15.4 |