Reinforcement Learning: Tabular and Approximation Methods vs Search Algorithms

Building on the previous meeting where we began using a Rubik's cube as a test environment, we will look at a simpler version of the problem (a pocket cube) and explore several approaches to solving it. This problem is simple enough that we can get an exact solution and thus judge the effectiveness of approximation methods from reinforcement learning as well as some other techniques like breadth first search and more efficient variations of it such as iterative deepening A*.

As usual you can find below links to the textbook, previous chapter notes, slides, and recordings of some of the previous meetings.

Useful Links:
Reinforcement Learning: An Introduction by Richard S. Sutton and Andrew G. Barto
Recordings of Previous Meetings
Short RL Tutorials
My exercise solutions and chapter notes
Kickoff Slides which contain other links
Video lectures from a similar course