genrl 0.0.1

A PyTorch reinforcement learning library for generalizable and reproducible implementations.

GenRL

Installation

We suggest creating a conda virtual environment before installing our package.

conda create -n JgRL_env python=3.6 pip
conda activate JgRL_env

From Source (Recommended)

git clone https://github.com/SforAiDl/genrl.git
cd genrl
pip install -r requirements.txt
python setup.py install

Using Pip

pip install genrl # for most recent stable release
pip install genrl==0.0.1dev2 # for most recent development release

Usage

from genrl import PPO1
import gym

env = gym.make('CartPole-v0')
agent = PPO1(network_type='mlp', env=env, epochs=500, render = True, tensorboard_log='./runs/')

agent.learn()