Artificial Curiosity

Adaptive Reinforcement Learning of curious AI basketball agent

A machine learning project of learning NBA shots success ratio based on 410,000 records of NBA players shots stats.

The project implement various ML techniques in order to create a "Curious" AI agent, which learns success ratios and implements the knowledge in exploration-exploitaition game simulation enviroment.

Part 1 - Bayesian Inference and Information Gain

After a EDA and preprocessing of shot data into categorical features we implemented a bayesian inference algorithm and evaluated the feature selection with Expected Information Gain criteria.

Part 2 - Neural Network Learning and Optimization

Manual Neural Network implementation with numpy and SGD method. This part required new preprocess methods (to continous features) and network structure optimization improving prediction AUC to 70%

Extra:

• Genetic algorithm optimization

  Implementation of genetic algorithm for network structure optimization

• Random Forest, SVM and PCA methods

  Benchmarks method for accuracy estimation and feature selection

Part 3 - Curiosity Loop with Adaptive Reinforcement Learning

Implementaion of Curosity Loop, using Actor-Critic Method and Bayesian Inference.

The Curiosity Loop:

A "new-born" AI agent takes shots from diffent positions and learns the success of each shot, while trying to both learn the enviroment and score as much as possible.

Project Presentation:

Link to project presentation (pdf)

More Links:

• Big Data Lab @ TAU
• Curiosity Lab @ TAU