Reinforcement Learning on Walker2d v4
39,641,353Avg Return
MDC-SAN
Updated 1mo ago
Evaluation Results
| Method | Links | |
|---|---|---|
2026.02 | 39,641,353 | |
2026.02 | 33,071,514 | |
2026.02 | 18,621,450 | |
2026.02 | 4,436,196 | |
2026.02 | 4,340,383 | |
2026.02 | 4,314,423 | |
2026.02 | 4,235,354 | |
2026.02 | 4,200,717 | |
2026.04 | 4,808 | |
2026.01 | 4,497 | |
2026.01 | 4,445 | |
2026.03 | 4,367.1 | |
2026.01 | 4,271 | |
2026.03 | 4,128.8 | |
2026.01 | 4,050 | |
2026.01 | 4,003 | |
2026.06 | 3,995 | |
2026.06 | 3,717 | |
2026.06 | 3,717 | |
2026.06 | 3,639 | |
2026.03 | 3,277 | |
2026.03 | 2,923.2 |