Reinforcement Learning - BKJackson/BKJackson_Wiki GitHub Wiki

Markov Decision Processes

CS 188 Lecture - Markov Decision Processes (MDPs) - Pieter Abbeel, UC Berkeley, - Covers grid world example w/value iteration, policy evaluation, and policy iteration.
CS 287 Lecture - Markov Decision Processes and Exact Solution Methods - Pieter Abbeel, - Covers value iteration, policy iteration, and linear programming

Video Lectures

Deep RL Bootcamp

Tutorials

Reinforcement Learning for Absolute Beginners Part 1 – With Python Programming With Material From: Reinforcement Learning: An Introduction “Sutton" Vitali Mueller
The very basics of Reinforcement Learning Aneek Das
Introduction to Q-Learning Aneek Das - Simple Python code example

Sequential decision problems (a version of RL)

From the jungle of stochastic optimization to… Sequential Decision Analytics
From Reinforcement Learning to Optimal Control: A unified framework for sequential decisions
Modeling Energy Storage with RL

Articles

How do machines plan? - An Introduction - A gentle introduction to graph search algorithms and Markov Decision Processes
World Models - Can agents learn inside of their own dreams?, March 27, 2018
The Paths Perspective on Value Learning - Comparison of Monte Carlo, Temporal Difference, and Q Learning. Sept. 30, 2019.
Bayesian Neural Networks with Random Inputs for Model Based Reinforcement Learning
Reinforcement Learning for Profit Kory W. Mathewson
Deep Deterministic Policy Gradients in TensorFlow Patrick Emami

Sample Code, Python Notebooks

garage RL toolkit - toolkit for developing and evaluating reinforcement learning algorithms
garage docs & examples
K-Armed Bandit Problem From Vitali Mueller tutorial above.

Courses

CMU 15-887A: AI Planning, Execution, and Learning - Lecture notes, Taught by Reid Simmons & Manuela Veloso, Fall 2001
Artificial Intelligence II - Lecture notes, Taught by Sean Holden, U. Cambridge (RL in notes in part 5, other content also useful)

Books

Reinforcement Learning: An Introduction Sutton and Barto