qihuanye
|
28f2fba0e8
|
加入一个提前停止的机制 还有减少环境步中间步骤传递至cpu
|
2026-05-18 00:48:59 +08:00 |
|
qihuanye
|
e84074d6d6
|
调整ignore的文件
|
2026-05-04 08:05:47 +00:00 |
|
qihuanye
|
cf43af0729
|
更改求解器 step=150时 成功率更高 step=125时 速度更快 成功率持平
|
2026-05-04 07:55:13 +00:00 |
|
qihuanye
|
25e4ddb628
|
继续做了通用性能优化，重点从 jepa.py 热路径转到实际的 stable_worldmodel
solver/policy 边界：去掉 CEM 每轮 cpu().tolist() 和结果过早回 CPU，把
plan/warm-start 保持在 GPU，只在 env.step 前最后一步转成 numpy，同时补
了输入张量的 contiguous 处理；
|
2026-04-09 12:33:50 +00:00 |
|
qihuanye
|
20ffb3492b
|
Disable Gym passive checker by default in stable_worldmodel env creation
|
2026-04-09 11:11:07 +00:00 |
|
qihuanye
|
0f85e39690
|
Reduce evaluation overhead with parallel video saving
|
2026-04-08 13:56:57 +00:00 |
|
qihuanye
|
85795bd91d
|
Vectorize image preprocessing in stable_worldmodel policy
|
2026-04-08 13:48:19 +00:00 |
|
qihuanye
|
12ba4f4352
|
Optimize CEM input transfers before sample expansion
|
2026-04-08 13:01:24 +00:00 |
|