Reinforcement Learning on DMC-GB2 Video Hard (test)
725Cartpole Swingup ReturnT2RD
Evaluation Results
| Method | Links | |||||||
|---|---|---|---|---|---|---|---|---|
| T2RD2026.07 | 725 | — | 616 | 833 | 895 | 444 | — | |
| SGQN2026.07 | 544 | — | 782 | 822 | 851 | 739 | — | |
| BiT2026.07 | 526 | — | 570 | 400 | 829 | 325 | — | |
| EADream2026.01 | 449 | 240 | 288 | 400 | 872 | 613 | 477 | |
| SODA2026.07 | 429 | — | 327 | 302 | 771 | 312 | — | |
| PIE-G2026.07 | 401 | — | 786 | 762 | 852 | 600 | — | |
| SVEA2026.07 | 393 | — | 403 | 335 | 834 | 385 | — | |
| SADA2026.01 | 363 | 82 | 662 | 566 | 702 | 270 | 441 | |
| TRP2026.07 | 333 | — | 274 | 261 | 824 | 355 | — | |
| DreamerV32026.01 | 296 | 228 | 53 | 99 | 816 | 569 | 343 | |
| SVEA2026.01 | 259 | 28 | 416 | 263 | 429 | 264 | 277 | |
| TLDA2026.07 | 223 | — | 457 | 224 | 769 | 271 | — | |
| DyMoDreamer2026.01 | 138 | 127 | 92 | 205 | 809 | 664 | 339 | |
| DrQ2026.07 | 136 | — | 100 | 38 | 252 | 121 | — | |
| DrQ2026.01 | 98 | 25 | 111 | 7 | 154 | 36 | 72 |