Python code, PDFs and resources for the series of posts on Reinforcement Learning which I published on my personal blog

A blog which talks about machine learning, deep learning algorithms and the Math. and Machine learning algorithms written from scratch.

A course on Deep Reinforcement Learning in Computer Vision. Visit Website:

[INACTIVE] A collection of various machine learning solver. The library is an object-oriented approach (baked with Typescript) and tries to deliver simplified interfaces that make using the algorithms pretty simple.

Backgammon OpenAI Gym

Basic Reinforcement Learning algorithms

Introduction to Reinforcement Learning in Python

Reinforcement Learning algorithms with nothing abstracted away

PyTorch implementation of the Munchausen Reinforcement Learning Algorithms M-DQN and M-IQN

A self-learning chess artificial intelligence

TD-Gammon implementation

This repository has all the codes and sources of various RL algorithms that I have implemented.

Temporal Difference Learning for Game 2048 (Demo)

Implemented AdaTD and compared it with other optimization methods in temporal difference learning.

Python implementation and analysis of two reinforcement algorithms – monte carlo and temporal differencing

Watch the AI learn to play Meta-Tic-Tac-Toe:

Temporal difference mini project from the reinforcement learning section of Udacity's Machine Learning Nanodegree (MLND). This mini project wasn't required to be turned in; used as a teaching tool.

Einreichung für die it-talents.de/Adesso Code-Competition Oktober 2017 ("Kampf gegen Mühlen"). Eine ES6-Webapplikation auf Basis von vue.js, fabric.js und synaptic für das Spiel Mühle im Browser. Es stehen unterschiedlich starke AI mit diversen Charakteristika zur Verfuegung. Das Spiel und AI laufen komplett im Browser als WebWorker.

Reinforcement Learning tool to show how λ and learning rate affect Q(λ). Demonstrates this through teaching a bot to solve a maze.

Various computational models for reinforcement learning

Various fundamental reinforcement learning algorithms implemented from scratch

My RL Project (2048 World Record + IEEE TCIAIG Journal Source Code)

Lecture for AgileSoda

Solving The Royal Game of Ur using Reinforcement Learning - Monte Carlo, TD Methods, Dynamic Programming, DQN

Foundations Of Intelligent Learning Agents (FILA) Assignments

Assignments for CS747 - Foundations of Intelligent and Learning Agents

Various reinforcement learning algorithms implemented using Python. This repo also contains a DQN approach to solve credit-card anomaly detection use-case.

My solution notebooks for the Deep Reinforcement Learning Nanodegree by Udacity

Train a Tic-Tac-Toe and a Connect-4 player using the TD-lambda algorithm