LearningX Examples and Tutorials

We provide here a suite of Python examples that walk you through concepts in:

• Classical & Deep Reinforcement Learning

• Basic & Advanced Machine Learning

Usage of the examples is simple: just run the main file for each project. Each project example contains its own README.md file discussing the theory and applications.

Classical Reinforcement Learning

The Multi-Armed Bandit Problem

Q-Learning in GridWorld

Optimal Blackjack Strategy

Deep Reinforcement Learning

Balancing Cartpole Beam on OpenAI gym

Playing Pong from pixels on OpenAI gym

Basic Machine Learning

Classification

• Decision Tree, K-Nearest Neighbours, Logistic Regression (Gradient Descent)

Regression

• Linear Regression (Gradient Descent / Stochastic Gradient Descent)

Unsupervised Learning

• K-means Clustering

Advanced Machine Learning

Building Model Trees

Tree Ensembles: Bagging and Boosting

Author

Anson Wong