joyrl 0.4.4.1

A Library for Deep Reinforcement Learning

JoyRL

JoyRL is a parallel reinforcement learning library based on PyTorch and Ray. Unlike existing RL libraries, JoyRL is helping users to release the burden of implementing algorithms with tough details, unfriendly APIs, and etc. JoyRL is designed for users to train and test RL algorithms with only hyperparameters configuration, which is mush easier for beginners to learn and use. Also, JoyRL supports plenties of state-of-art RL algorithms including RLHF(core of ChatGPT)(See algorithms below). JoyRL provides a modularized framework for users as well to customize their own algorithms and environments.

Install

⚠️ Note that donot install JoyRL through any mirror image!!!

# you need to install Anaconda first
conda create -n joyrl python=3.8
conda activate joyrl
pip install -U joyrl

Torch install:

Pip install is recommended, but if you encounter network error, you can try conda install or pip install with mirrors.

# pip CPU only
pip install torch==1.10.0 torchvision==0.11.0 torchaudio==0.10.0
# if network error, then GPU with mirror image
pip install torch==1.10.0+cu113 torchvision==0.11.0+cu113 torchaudio==0.10.0 --extra-index-url https://download.pytorch.org/whl/cu113
# CPU only
conda install pytorch==1.10.0 torchvision==0.11.0 torchaudio==0.10.0 cpuonly -c pytorch
# GPU 
conda install pytorch==1.10.0 torchvision==0.11.0 torchaudio==0.10.0 cudatoolkit=11.3 -c pytorch -c conda-forge

Usage

Quick Start

the following presents a demo to use joyrl. As you can see, first create a yaml file to config hyperparameters, then run the command as below in your terminal. That's all you need to do to train a DQN agent on CartPole-v1 environment.

joyrl --yaml ./presets/ClassControl/CartPole-v1/CartPole-v1_DQN.yaml

or you can run the following code in your python file.

import joyrl
if __name__ == "__main__":
    print(joyrl.__version__)
    yaml_path = "./presets/ClassControl/CartPole-v1/CartPole-v1_DQN.yaml"
    joyrl.run(yaml_path = yaml_path)

Offline Run

If you want to run from source code for debugging or other purposes, you can clone this repo:

git clone https://github.com/datawhalechina/joyrl.git

Then install the dependencies:

pip install -r requirements.txt
# if you have installed joyrl, you'd better uninstall it to avoid conflicts
pip uninstall joyrl

Then you can run the following command to train a DQN agent on CartPole-v1 environment.

python offline_run.py --yaml ./presets/ClassControl/CartPole-v1/CartPole-v1_DQN.yaml

Documentation

More tutorials and API documentation are hosted on JoyRL docs or JoyRL 中文文档.

Algorithms

Name	Reference	Author	Notes
DQN	DQN Paper	johnjim0816