https://github.com/yandexdataschool/gumbel_dpg
Blog post: how to do deterministic policy gradient with gumbel softmax and why you should do it.
https://github.com/yandexdataschool/gumbel_dpg
Last synced: 2 months ago
JSON representation
Blog post: how to do deterministic policy gradient with gumbel softmax and why you should do it.
- Host: GitHub
- URL: https://github.com/yandexdataschool/gumbel_dpg
- Owner: yandexdataschool
- License: mit
- Created: 2017-06-16T10:37:40.000Z (about 8 years ago)
- Default Branch: master
- Last Pushed: 2017-06-20T19:19:24.000Z (almost 8 years ago)
- Last Synced: 2023-08-03T13:59:42.448Z (almost 2 years ago)
- Language: Jupyter Notebook
- Size: 87.9 KB
- Stars: 11
- Watchers: 3
- Forks: 3
- Open Issues: 0