Awesome AI Agents › Educational & Learning Agents

ankonzoid/LearningX

⭐ 365 Python added to this list on 2025-04-19 repository created 2017-09-10

LearningX is a comprehensive Python project that offers a wide range of examples and tutorials covering both classical and deep reinforcement learning as well as basic and advanced machine learning techniques. The repository is structured to provide hands-on experience through runnable main files for each example, accompanied by detailed README.md files that explain the underlying theory and practical applications. The classical reinforcement learning section includes projects such as the Multi-Armed Bandit Problem, Q-Learning in GridWorld, and Optimal Blackjack Strategy, which introduce foundational concepts and algorithms in reinforcement learning. The deep reinforcement learning section features examples like balancing a Cartpole beam and playing Pong using OpenAI Gym environments, demonstrating the application of neural networks and deep learning methods to reinforcement learning tasks. In the basic machine learning category, the project covers essential algorithms including decision trees, k-nearest neighbors, logistic regression, linear regression, and k-means clustering, providing a solid foundation in supervised and unsupervised learning. The advanced machine learning section delves into more complex topics such as building model trees and ensemble methods like bagging and boosting, which are crucial for improving model performance and robustness. Each example is designed to be easily executable, making it accessible for learners to experiment and understand the concepts through practical implementation. The project is authored by Anson Wong and serves as an educational resource for those interested in gaining a deeper understanding of machine learning and reinforcement learning through code examples and tutorials.

https://github.com/ankonzoid/LearningX

advanced-machine-learningagentbaggingbasic-machine-learningblackjack-strategyboostingcartpoleclassical-reinforcement-learningclassificationdata-sciencedeepdeep-learningdeep-reinforcement-learningexamplesgridworldk-means-clusteringlearningmachine-learningmachine-learning-algorithmsmodel-treesmulti-armed-banditmultiagent-reinforcement-learningneural-networkopenai-gymoptimizationpongpythonq-learningregressionreinforcement-learningtree-ensemblestutorial-codetutorial-exercisestutorialsunsupervised-learning