hongshaorou/Tianshou
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Merge branch 'master' of github.com:sproblvem/tianshou

Browse Source
This commit is contained in:
Dong Yan 2017-12-19 00:16:33 +08:00
commit 243bbaff64
2 changed files with 4 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
.gitignore vendored
View File

@ -7,3 +7,4 @@ parameters
checkpoints checkpoints
checkpoints_origin checkpoints_origin
*.json *.json
.DS_Store

4
README.md
View File

@ -46,6 +46,8 @@ Tianshou(天授) is a reinforcement learning platform. The following image illus
Please follow [google python coding style](https://google.github.io/styleguide/pyguide.html) Please follow [google python coding style](https://google.github.io/styleguide/pyguide.html)
There's a more detailed Chinese version [google python coding style in Chinese](http://www.runoob.com/w3cnote/google-python-styleguide.html)
All files/folders should be named with lower case letters and underline (except specified names such as `AlphaGo`). All files/folders should be named with lower case letters and underline (except specified names such as `AlphaGo`).
Try to use full names. Don't use abbrevations for class/function/variable names except common abbrevations (such as `num` for number, `dim` for dimension, `env` for environment, `op` for operation). For now we use `pi` to refer to the policy in examples/ppo_example.py. Try to use full names. Don't use abbrevations for class/function/variable names except common abbrevations (such as `num` for number, `dim` for dimension, `env` for environment, `op` for operation). For now we use `pi` to refer to the policy in examples/ppo_example.py.
@ -73,4 +75,4 @@ HaoshengZou: collaborate mainly on Policy and losses; interfaces and architectur
Note: install openai/gym first to run the Atari environment; note that interfaces between modules may not be finalized; the management of placeholders and `feed_dict` may have to be done manually for the time being; Note: install openai/gym first to run the Atari environment; note that interfaces between modules may not be finalized; the management of placeholders and `feed_dict` may have to be done manually for the time being;
Without preprocessing and other tricks, this example will not train to any meaningful results. Codes should past two tests: individual module test and run through this example code. Without preprocessing and other tricks, this example will not train to any meaningful results. Codes should past two tests: individual module test and run through this example code.