Reinforcement Learning on Ant v5
6,633.8Average Return
QVPO+DBC(*)
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.02 | 6,633.8 | |
2026.02 | 6,501.4 | |
2026.02 | 6,373.2 | |
2026.02 | 6,342.6 | |
2026.02 | 6,121.8 | |
2026.02 | 5,306 | |
2025.12 | 4,477.33 | |
2026.02 | 4,257 | |
2026.03 | 4,183 | |
2026.03 | 4,125 | |
2025.12 | 4,067.61 | |
2026.02 | 4,000 | |
2026.02 | 4,000 | |
2026.02 | 3,850.4 | |
2025.12 | 3,761.98 | |
2026.02 | 3,750 | |
2026.02 | 3,662 | |
2026.03 | 3,570 | |
2026.02 | 3,536 | |
2026.02 | 3,487.4 | |
2026.02 | 3,474 | |
2026.02 | 3,389 | |
2026.02 | 3,190 | |
2026.02 | 3,169 | |
2026.03 | 3,157 | |
2026.02 | 3,093 | |
2026.02 | 3,084 | |
2026.02 | 3,082 | |
2026.02 | 2,963 | |
2026.02 | 2,830 | |
2026.02 | 2,818 | |
2026.02 | 2,792 | |
2026.02 | 2,781 | |
2026.02 | 2,663 | |
2026.02 | 2,650.3 | |
2025.12 | 2,619.72 | |
2026.02 | 2,013.2 | |
2026.02 | 1,225 | |
2026.02 | 1,221 | |
2026.02 | 994 | |
2025.12 | 960.36 | |
2025.12 | 959.65 | |
2025.12 | 958.54 | |
2025.12 | 957.37 | |
2026.02 | 957 | |
2025.12 | 954.13 | |
2025.12 | 953.84 | |
2025.12 | 948.86 | |
2025.12 | 934.15 | |
2026.03 | 610 | |
2026.03 | 501 | |
2026.03 | 456 | |
2026.03 | 376 | |
2025.12 | 155.64 | |
2025.12 | 32.47 | |
2025.12 | 17.34 | |
2025.12 | -11.15 |