Resources on Reinforcement Learning

<Previous | Next | Contents>

INTRODUCTION & TUTORIAL

• Online book Reinforcement Learning by Sutton and Barto (HTML) . Check Prof. Richard S. Sutton Page here
• FAQ about Reinforcement Learning
• Reinforcement Learning by Dayan and Watkins
• Temporal Difference Learning and TD-Gammon By Gerald Tesauro (classical paper mark the success of RL)
• Reinforcement Learning: A Survey by Leslie Pack Kaelbling, Michael L. Littman and Andrew W. Moore
• Extending Q-Learning to General Adaptive Multi-Agent Systems by Gerald Tesauro
• Mark Humphrys dissertation contain how Q learning work, discrete Q learning
• Harmon's Reinforcement Learning Tutorial (PDF) - classical teaching material
• Statistical Data Mining of Andrew Moore
• Geri Tesauro Multi Agent Learning Mini Tutorial (PPT)
• Hagen and Krose short Intro to Reinforcement Learning (PDF)
• Gosavi Reinforcement Learning tutorial
• Colorado State Univ Reinforcement Learning and Control
• Teknomo tutorial on Simple learning
• Calgary Intro to AI - Reinforcement Learning PPT
• Wiering handout on RL and NN (PDF)
• Salsa Introduction to Reinforcement Learning

ARTICLES

• Reinforcement Learning With Self-Modifying Policies
• Bayesian Q Learning by R. Dearden, N. Friedman, and S. Russell
• Multigrid Q-Learning by Charles W. Anderson and Stewart G. Crawford-Hines
• Improving Generalisation for Temporal Difference Learning: The Successor Representation by Peter Dayan
• Reinforcement Learning for Stochastic Cooperative Multi-Agent-Systems by Martin Lauer and Martin Riedmiller
• Feudal Reinforcement Learning by Peter Dayan and Geoffrey E Hinton
• A New Q-Learning Algorithm Based on the Metropolis Criterion by Maozu Guo, Yang Liu, and Jacek Malec

APPLICATIONS

• Oil Market Modeling Using Q-Learning by Michael Wunder
• Pricing in agent economies using multi-agent Q-learning by Gerald Tesauro and Jeffrey O. Kephart
• Multi-agent Q-learning and Regression Trees for Automated Pricing Decisions by Manu Sridharan and Gerald J. Tesauro
• Reinforcement Learning and its Application to Othello by Nees Jan van Eck, Michiel van Wezel
• Reinforcement Learning applied to a Radar Tracking Task (Java Applet provided)
• Car Simulation Using Reinforcement Learning by Zhijin Wang

SOFTWARE & CODE

• RIL- Reinforcement Learning Toolbox - C++ free download
• Dr. Mark Humphrys provides Q-Learning code in C++ using lookup table
• Kardi Teknomo's Q Learning by Example Matlab code and MS Excel
• Check Sutton's Software page (Reinforcement Learning implementattion in C, C++ and Lisp)
• Java Code of Reinforcement Learning provided by Gettysburg College. See the paper related to the code here.
• Connectionist Q-learning Java Framework is an Open Source Java library for developing simple or complicated learning systems
• Thierry Masson wrote Java applet of Q-learning

Q-LEARNING

• Zarul Hamzah essay: Are we learning now?
• Michael Bowling reading for
• EPFL- Java Black Jack and Reinforcement Learning (Applet)

OTHER EXCELLENT RESOURCES

• AAAI - American Association for Artificial Intelligence Reinforcement learning page
• Reinforcement Learning Repository
• Reinforcment Learning warehouse AI Depot (nice introduction)
• Machine Learning and Friends at CMU

Books (references)

• Mitchell, T. M. (1997) Machine Learning, McGrawHill
• Sutton, R.S. and Barto, A.G. (1998), Reinforcement Learning – an Introduction, MIT Press

<Previous | Next | Contents>