Implementation of 4 different BlackJack RL algorithims for Basic BlackJack Environment and Complete Card Count System Environment based on my research.The references of books and papers are included in my research paper pdf. The names of implemented RL Algorithims are:
-
SARSA(on-Policy)
-
TD(Temporal Difference off-Policy)
-
Monte Carlo on-Policy
-
Monte Carlo off-Policy
All these Algorithims has been deployed and tested for both Environments.