Tensorflow implementation of Proximal Policy Optimization Algorithms
Basic Policy-Gradient model is hard to trainning very likely,so the enhanced version has appeared.
If you don't know basic Policy-Gradient algorithm or have no experience about training Basic Policy-Gradient model,I suggest you look at my project:"Basic_Policy_Gradient" first.
This is an implementation of basic Proximal Policy Optimization Algorithm to play the game:"CartPole-v0" and "Pendulum-v0".
You can Change code to play other OpenAi Gym games. You can also Optimize this algorithm.
If you want to exchange ideas with me，you can add me to WeChat:zggcdbs.
zhibindaxia/RL-PPO-Tensorflow
Tensorflow implementation of Proximal Policy Optimization Algorithms
Python