hongshaorou/Tianshou

Go to file

haoshengzou bdd85f8a27 stop gradient in policy/distributional

2018-12-24 09:06:59 +08:00

fix code example in tutorial. leave render to be future work

2018-05-29 11:04:32 +08:00

stop gradient in policy/distributional

2018-12-24 09:06:59 +08:00

stop gradient in policy/distributional

2018-12-24 09:06:59 +08:00

.gitignore

advantage estimation function all take my_feed_dict (all examples runnable); such requirement should be made a signature

2018-11-22 08:03:03 +08:00

internal_keys.md

interfaces for advantage_estimation. full_return finished and tested.

2018-02-27 14:11:52 +08:00

LICENSE

Initial commit

2017-11-04 01:38:59 +08:00

README.md

first master version

2018-04-16 18:02:00 +08:00

setup.py

stop gradient in policy/distributional

2018-12-24 09:06:59 +08:00

README.md

TianShou

TianShou(天授) is a reinforcement learning platform.

For now, tutorials and API docs are hosted on http://ml.cs.tsinghua.edu.cn/~haosheng/tianshou/

Installation

For now, please clone this repository and run

pip install .

in the cloned main directory.

Dependency

Python (only tested with version 3.x)

TensorFlow (version >= 1.4)

OpenAI Gym