Implementation of PPO (Proximal Policy Optimization)

This is a tensorflow implementation of proximal policy optimization (PPO) algorithm for continuous action

Original Paper

here

Demo

Results

Total Scores Vs Number of iteration (Pendulum-v0)

Losses (Pendulum-v0)

Dependencies

• python 3.5
• tensorflow 1.1.0
• openAI

Usage

For Training Run:

$ python3 trainer.py

For Demo Run:

$ python3 play.py

Credit

Reference Project

PPO