/PPO_pendulmn

Swinging up a pendulmn by PPO(Proximal Policy Optimization)

Primary LanguagePythonMIT LicenseMIT

PPO_pendulmn

Swinging up a pendulmn by PPO(Proximal Policy Optimization)

Please refer to this Qiita entry.

movie

Usage

train

python run_pendulumn.py train

replay

python run_pendulumn.py replay

If you need movie (animation gif) file, set RECORD_MOVIE=True in the script run_pendulmn.py to output serial numbered png file and exec:

cd movie
./conv.sh

plot learning curve

python plot_log.py

License

MIT