Reinforcement-Learning

Reinforcement-Learning copied to clipboard

I believe the Question of Exercise 2.2: Bandit Example is incorrect. The R1 value and R3 values should be -1 and -2 respectively as per the second edition of the book.

1


C3Suryansu

There is an old answer of exercise 4.1 in this file: http://fumblog.um.ac.ir/gallery/839/weatherwax_sutton_solutions_manual.pdf qπ (11, down) =0 Are you sure of the answer -1 of exercise 4.1?

archcra