8x54zj-m
|
a0e8501d11
|
Add independent DreamWaQ stair capability benchmark
|
2026-07-22 16:31:09 +08:00 |
|
8x54zj-m
|
0555776c11
|
Align DreamWaQ PPO rollout and policy dynamics
|
2026-07-22 13:59:16 +08:00 |
|
8x54zj-m
|
1072565d97
|
Fix action smoothing history and viewer timing control
|
2026-07-22 13:25:17 +08:00 |
|
8x54zj-m
|
660393a9ee
|
Add closed-loop DreamWaQ stair validation
|
2026-07-22 02:36:36 +08:00 |
|
8x54zj-m
|
3648551043
|
Backup DreamWaQ rslrl stability fixes
|
2026-07-22 02:17:01 +08:00 |
|
8x54zj-m
|
63b235d186
|
fix: MuJoCo sim2sim default_angles match MotrixSim training
|
2026-07-01 20:55:16 +08:00 |
|
8x54zj-m
|
3038aa7ac7
|
fix: critic called once (was 3x), adaptive KL schedule restored, upgrade 3m
|
2026-07-01 15:05:50 +08:00 |
|
8x54zj-m
|
b0f1da4596
|
fix: clamp std before distribution, lower init_noise to 0.5, NaN guard
|
2026-06-30 15:35:58 +08:00 |
|