https://github.com/sonnhfit/deepair

PyTorch implementations of Deep reinforcement learning algorithms.
https://github.com/sonnhfit/deepair

deep-reinforcement-learning dqn-pytorch rainbow reinforcement-learning

Last synced: about 1 year ago
JSON representation

PyTorch implementations of Deep reinforcement learning algorithms.

• Host: GitHub
• URL: https://github.com/sonnhfit/deepair
• Owner: sonnhfit
• License: mit
• Created: 2022-05-30T18:56:52.000Z (about 4 years ago)
• Default Branch: main
• Last Pushed: 2022-07-29T07:25:51.000Z (almost 4 years ago)
• Last Synced: 2025-03-18T14:53:42.928Z (about 1 year ago)
• Topics: deep-reinforcement-learning, dqn-pytorch, rainbow, reinforcement-learning
• Language: Python
• Homepage: https://deepair.readthedocs.io
• Size: 669 KB
• Stars: 5
• Watchers: 1
• Forks: 0
• Open Issues: 3
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# Deepair is a Deep Reinforcement Learning library

[![PyPI version](https://badge.fury.io/py/deepair.svg)](https://badge.fury.io/py/deepair)

[![Documentation Status](https://readthedocs.org/projects/deepair/badge/?version=latest)](https://deepair.readthedocs.io/en/latest/?badge=latest)

Deepair implementations of reinforcement learning algorithms. It focus on DRL algorithms and implementing the latest advancements in DRL. Highly customizable support for training processes. Suitable for the research and application of the latest technologies in reinforcement learning.

# Features

# Documentation

Documentation is available: [https://deepair.readthedocs.io/](https://deepair.readthedocs.io/)

# Installation

```

pip install deepair

```

or

```

pip install git+https://github.com/sonnhfit/deepair.git

```

# Example

```python

import gym

from deepair.dqn import Rainbow

env = gym.make('LunarLander-v2')

rain = Rainbow(env=env, memory_size=10000, batch_size=32, target_update=256)

rain.train(timesteps=200000)

# test

state = env.reset()

done = False

score = 0

while not done:

    action = rain.select_action(state, deterministic=True)

    next_state, reward, done, info = env.step(action)

    state = next_state

    score += reward

print("score: ", score)

```

![rainbow lunalander env](docs/source/_static/img/rainbow_lunalander.gif)

# Implemented Algorithms

# Tutorial

- save model 

- load model

# How To Contribute