reinforcement-learning-course

Winter Semester 2018/2019 - Albert-Ludwigs-Universität Freiburg

Introduction

In this repository you will find different exercises for Reinforcement Learning, such as Markov Processes, Bellman Equations, Dynamic Programming or Model-free Prediction and Control.

Glossary

• Exercise 00: OpenAI Gym Tutorial
• Exercise 01: Markov Decision Processes, Markov Properties and Bellman Equation
• Exercise 02: Dynamic Programming
• Exercise 03: Model-free Prediction (Monte-Carlo)
• Exercise 04: Model-free Control (Off-Policy Monte-Carlo) and Q-Learning
• Exercise 05: Q-Learning with Function Aproximation
• Exercise 06: Advanced Policy Gradient Algorithms (REINFORCE)
• Exercise 07: Advanced Policy Gradient Algorithms (PPO)
• Exercise 08: UCB1
• Project: CartPole