sitexa / ptan

PyTorch Agent Net: reinforcement learning toolkit for pytorch

PTAN

PTAN stands for PyTorch AgentNet -- reimplementation of AgentNet library for PyTorch

This library was used in "Deep Reinforcement Learning Hands-On" book, here you can find sample sources.

Code branches

The repository is forked from https://github.com/Shmuma/ptan .

The main work is to replace Gym with Gymnasium, upgrade torch version to meet the GPU upgrade to RTX4090。

Installation

From sources:

pip install -e . 

From pypi:

pip install ptan

From github:

pip install pip install git+https://github.com/Shmuma/ptan.git 

Requirements

• PyTorch: version 2.2.1 is required
• PyTorch Ignite: provides extra bindings for ignite
• OpenAI Gym: pip install gymnasium gymnasium[atari]
• Python OpenCV: pip install opencv-python
• TensorBoardX: pip install tensorboardX

Note for Anaconda Python users

To run some of the samples, you will need these modules:

conda install pytorch torchvision -c pytorch
pip install tensorboard-pytorch
pip install gymnasium
pip install gym[atari]
pip install opencv-python

Documentation

• Ptan introduction

Random pieces of information

• ExperienceSource vs ExperienceSourceFirstLast: Shmuma#17 (comment)