README.md

Reinforcement Learning and Game Theory

This repository is a work in progress.

This repository will provide supplementary material for the following books:

• Sutton's Reinforcement Learning Second Edition
• Dimitri Bertsekas' Reinforcement Learning and Optimal Control
• Blackwell's Theory of Games and Statistical Decisions

We will go through some of the examples and excercises in the books and will write a Python code for solving those.

For the books on Reinforcement Learning we will discuss and go through the following RL packages - PyQLearning, keras-rl, tensorforce, RL Coach, RLib.

For Game Theory we will discuss and go through the following packages: NashPy and Gambit.

Selected Topics in Machine Learning

• Reinforcement Learning and Game Theory

• Offline Reinforcement and Self-Supervised Learning

• NLP Concepts

• Transformers

• Large Language Models

• Bayesian Networks

• Probabilistic Machine Learning

• Optimization, Classification, Regression

• Causal Inference, Root Cause Analysis and Model Checking

• Deep Learning and Neural Networks

• Hypothesis Testing, Estimation of Treatment Effects and Generalized Synthetic Control

• Graphs and Dynamic Programming

• Dynamical Systems, State-Space Models, Chaos, Ergodicity

• Information Theory, Statistical Mechanics, Diffusion Models

• Queueing Networks, Queueing Theory, Reversible Stochastic Processes

• Spectral Analysis, Optimization in Spectral Domain, Spectral Domain Modeling

• Computability, Automata, Logic Systems, Formal Grammars and Theory of Parsing

• Thought Forming, Consciousness, Intelligent Machines, Inference, Logic Systems

Note

This repository uses git Large File Storage feature. In order to download locally the large files (> 1MB) which are maintained by git LFS you will need to install the Git extension for versioning large files: https://git-lfs.com/