DI-HPC is an acceleration operator component for general algorithm modules in reinforcement learning algorithms, such as GAE, n-step TD and LSTM, etc. The operators support forward and backward propagation, and can be used in training, data collection, and test modules.
Note: We recommend that DI-HPC and DI-Engine share the same environment, and it should be fine with PyTorch from 1.3.1 to 1.8.
The easiest way to get DI-HPC is to use pip, and you can get .whl
from
and then call
$ pip install <YOUR_WHL>
Alternatively you can install latest DI-HPC from git master branch:
$ python3 setup.py install
You will get benchmark result by following commands:
$ python3 tests/test_gae.py
此处可能存在不合适展示的内容,页面不予展示。您可通过相关编辑功能自查并修改。
如您确认内容无涉及 不当用语 / 纯广告导流 / 暴力 / 低俗色情 / 侵权 / 盗版 / 虚假 / 无价值内容或违法国家有关法律法规的内容,可点击提交进行申诉,我们将尽快为您处理。