Python Reinforcement Learning using OpenAI Gymnasium – Full Course
Offered By: freeCodeCamp
Course Description
Overview
Dive into a comprehensive tutorial on reinforcement learning using OpenAI Gymnasium, a Python library for developing and comparing reinforcement learning algorithms. Learn the fundamentals of reinforcement learning, including agent-environment interactions, and explore practical implementations using the Gymnasium API. Start with solving the Blackjack environment, understanding concepts like epsilon-greedy strategy and Q-values. Progress to more complex scenarios by tackling the Cartpole problem using Deep Q-Networks (DQN). Gain hands-on experience through guided coding exercises, visualizations of agent training, and access to a full Google Colab notebook. Conclude with an introduction to advanced topics, including Multi-Agent Reinforcement Learning using Pettingzoo. Perfect for learners seeking to master reinforcement learning techniques and their real-world applications in Python.
Syllabus
⌨️ Introduction
⌨️ Reinforcement Learning Basics Agent and Environment
⌨️ Introduction to OpenAI Gymnasium
⌨️ Blackjack Rules and Implementation in Gymnasium
⌨️ Solving Blackjack
⌨️ Install and Import Libraries
⌨️ Observing the Environment
⌨️ Executing an Action in the Environment
⌨️ Understand and Implement Epsilon-greedy Strategy to Solve Blackjack
⌨️ Understand the Q-values
⌨️ Training the Agent to Play Blackjack
⌨️ Visualize the Training of Agent Playing Blackjack
⌨️ Summary of Solving Blackjack
⌨️ Solving Cartpole Using Deep-Q-NetworksDQN
⌨️ Summary of Solving Cartpole
⌨️ Advanced Topics and Introduction to Multi-Agent Reinforcement Learning using Pettingzoo
Taught by
freeCodeCamp.org
Related Courses
Artificial Intelligence for RoboticsStanford University via Udacity Intro to Computer Science
University of Virginia via Udacity Design of Computer Programs
Stanford University via Udacity Web Development
Udacity Programming Languages
University of Virginia via Udacity