Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Collection of Python code that solves the Gymnasium Reinforcement Learning environments, along with YouTube tutorials.
| Date | Stars |
|---|---|
| 2026-07-31 | 262 |
| 2026-08-03 | 262 |
| 2026-08-04 | 262 |
| 2026-08-05 | 262 |
| 2026-08-06 | 262 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
<a name="readme-top"></a>
<h1 align="center">Gymnasium (Deep) Reinforcement Learning Tutorials</h1>
This repository contains a collection of Python code that solves/trains Reinforcement Learning environments from the [Gymnasium Library](https://gymnasium.farama.org/), formerly OpenAI’s Gym library. Each solution is accompanied by a video tutorial on my YouTube channel, [@johnnycode](https://www.youtube.com/@johnnycode), containing explanations and code walkthroughs. If you find the code and tutorials helpful, please consider supporting my work:
<a href='https://www.buymeacoffee.com/johnnycode'><img src="https://cdn.buymeacoffee.com/buttons/default-blue.png" alt="Buy Me A Coffee" height="41" width="174"></a>
<br />
# Train Atari Games <!-- omit from toc -->
If you want to jump straight into training AI agents to play Atari games, this tutorial requires no coding and no reinforcement learning experience! We use RL Baselines3 Zoo, a powerful training framework that lets you train and test AI models easily through a command line interface.
<a href='https://youtu.be/aQsaH7Tzvp0'><img src='https://img.youtube.com/vi/aQsaH7Tzvp0/0.jpg' width='400' alt='Full Guide: Easiest Way to Train AI to Play Atari Games with Deep Reinforcement Learning'/></a>
<br />
If you want to learn Reinforcement Learning:
- [Installation](#installation)
- [Beginner Reinforcement Learning Tutorials](#beginner-reinforcement-learning-tutorials)
- [1. Q-Learning on Gymnasium FrozenLake-v1 (8x8 Tiles)](#1-q-learning-on-gymnasium-frozenlake-v1-8x8-tiles)
- [Watch Q-Learning Values Change During Training on Gymnasium FrozenLake-v1](#watch-q-learning-values-change-during-training-on-gymnasium-frozenlake-v1)
- [2. Q-Learning on Gymnasium Taxi-v3 (Multiple Objectives)](#2-q-learning-on-gymnasium-taxi-v3-multiple-objectives)
- [3. Q-Learning on Gymnasium MountainCar-v0 (Continuous Observation Space)](#3-q-learning-on-gymnasium-mountaincar-v0-continuous-observation-space)
- [4. Q-Learning on Gymnasium CartPole-v1 (Multiple Continuous Observation Spaces)](#4-q-learning-on-gymnasium-cartpole-v1-multiple-continuous-observation-spaces)
- [5. Q-Learning on Gymnasium Acrobot-v1 (High Dimension Q-Table)](#5-q-learning-on-gymnasium-acrobot-v1-high-dimension-q-table)
- [6. Q-Learning on Gymnasium Pendulum-v1 (Continuous Action and Observation Spaces)](#6-q-learning-on-gymnasium-pendulum-v1-continuous-action-and-observation-spaces)
- [7. Q-Learning on Gymnasium MountainCarContinuous-v0 (Stuck in Local Optima)](#7-q-learning-on-gymnasium-mountaincarcontinuous-v0-stuck-in-local-optima)
- [Deep Reinforcement Learning Tutorials](#deep-reinforcement-learning-tutorials)
- [Getting Started with Neural Networks](#getting-started-with-neural-networks)
- [Deep Q-Learning a.k.a Deep Q-Network (DQN) Explained](#deep-q-learning-aka-deep-q-network-dqn-explained)
- [Implement DQN with PyTorch and Train Flappy Bird](#implement-dqn-with-pytorch-and-train-flappy-bird)
- [Apply DQN to Gymnasium Mountain Car](#apply-dqn-to-gymnasium-mountain-car)
- [Get Started with Convolutional Neural Network (CNN)](#get-started-with-convolutional-neural-network-cnn)
- [Stable Baselines3 Tutorials](#stable-baselines3-tutorials)
- [Stable Baselines3: Get Started Guide | Train Gymnasium MuJoCo Humanoid-v4](#stable-baselines3-get-started-guide--train-gymnasium-mujoco-humanoid-v4)
- [Stable Baselines3 - Beginner's Guide to Choosing RL Algorithms for Training](#stable-baselines3---beginners-guide-to-choosing-rl-algorithms-for-training)
- [Stable Baselines3: Dynamically Load RL Algorithm for Training | Train Gymnasium Pendulum](#stable-baselines3-dynamically-load-rl-algorithm-for-training--train-gymnasium-pendulum)
- [Automatically Stop Training When Best Model is Found in Stable Baselines3](#automatically-stop-training-when-best-model-is-found-in-stable-baselines3)
<br />
# Installation
The [Gymnasium Library](https://gymnasium.farama.orgExcerpt of 19,589 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:40906b6439335273, llm:description: 'Collection of Python code that solves the Gymnasium Reinforcement Learning environments, along with YouTube tutorials.'
matched fp:40906b6439335273, llm:description: 'Collection of Python code that solves the Gymnasium Reinforcement Learning environments, along with YouTube tutorials.'