Quality-Diversity Reinforcement Learning on Walker2d MuJoCo v4 (archive)
8.42QD-ScoreSV-QD-RL
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| SV-QD-RL2026.06 | 8.42 | 31.48 | 787 | 4,548.2 | 1,456.3 | |
| MAP-Elites2026.06 | 7.91 | 4.36 | 109 | 1,337.5 | 952.2 | |
| NSLC2026.06 | 6.5 | 4.96 | 124 | 1,359.6 | 711.4 | |
| QDAC2026.06 | 6.06 | 24.92 | 623 | 1,916.3 | 472.2 | |
| CMA-MAEGA2026.06 | 5.48 | 6.64 | 166 | 1,116.7 | 284.8 | |
| PGA-MAP-Elites2026.06 | 1.41 | 11.56 | 289 | 2,574.1 | 303.5 | |
| DNS2026.06 | 1.2 | 7 | 175 | 1,217.5 | 461.9 | |
| EDOCS2026.06 | 1.09 | 5.92 | 148 | 1,375.8 | 754.3 |