from David Mount !
Alternate Lecture notes at:
- https://www.cs.umd.edu/users/meesh/cmsc351/mount/lectures/
- https://www.cs.umd.edu/~mount/251/Lects/251lects.pdf
This is CMSC389F, the University of Maryland's theoretical introduction to the art of reinforcement learning. An introductory course taught by Kevin Chen and Zack Khan, CMSC389F covers topics including markov decision processes, monte carlo methods, policy gradient methods, exploration, and application towards real environments in broad strokes .