Cheryl0605 / RL-PPO-Keras

Proximal Policy Optimization(PPO) with Keras Implementation

RL-PPO-Keras

This is an implementation of proximal policy optimization(PPO) algorithm with Keras.

Usage

Start an experiment:

python main.py

Code

• run_exp.py

  Create environment and agent. Agent interacts with enviornment and learns with samples.

• config.py

  Configuration about agent, environment, experiment, and path.

• ppo.py

  Implementation of PPO algorithm.