On-Policy Monte Carlo Sampling for value function estimation. For a conceptual introduction, visit my blog : https://sridhartee.blogspot.in/2016/09/every-visit-exploring-starts-monte.html Takes Millions of iterations to converge to optimal policy. states.xls contains the states in the blackjack game. Run main.m function for starting value function esstimation.
-
Notifications
You must be signed in to change notification settings - Fork 0
License
sritee/MC-Exploring-Starts-Blackjack
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
Resources
License
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published