/ppo_tf

Implementation of proximal policy optimization(PPO) with tensorflow

Primary LanguagePythonMIT LicenseMIT

PPO_tf

Implementation of proximal policy optimization(PPO) using tensorflow

environment

CartPole-v0 of open ai gym
state space: continuous
action space: discrete

dependencies

python3.6
tensorflow v1.4
open ai gym

Training

python main.py

Test trained policy

python test_policy.py

Tensorboard

tensorboard --logdir=log

LICENSE

MIT ICENSE