Classical Planning & Reinforcement Learning
These are the notes and slides for the Graduate subject COMP90054 AI for Autonomy offered within the School of Computing and Information Systems, The University of Melbourne.
Textbooks
Classical Planning
- A Concise Introduction to Models and Methods for Automated Planning, Hector Geffner and Blai Bonet, Springer Nature (2013) - available via institutional (University of Melbourne) login
- An Introduction to the Planning Domain Definition Langauge, Patrik Haslum, Nir Lipovetzky, Daniele Magazzeni, and Christian Muise, Springer (2019) - available via institutional login
Reinforcement Learning
- Reinforcement Learning, An Introduction\(^1\) by Richard Sutton and Andrew Barto, Second Edition MIT Press (2020) (available for download at http://www.incompleteideas.net/book/RLbook2020.pdf)
Additional References
Artificial Intelligence (Introduction to Search)
- Artificial Intelligence: A Modern Approach, Stuart Russell and Peter Norvig, 2020 - see Chapter 3 & 4 on search - available via institutional login
The reinforcement learning slides contain examples and material adapted with the kind permission of David Silver, from Reinforcement Learning Slides\(^2\) which are licensed under the Creative Commons license CC BY-NC 4.0. The version of reinforcement learning slides here are also covered under the same license.