Optimal policy compared to any Random policy:
Optimal policy reached by Monte Carlo Method:
AkshayKulkarni3467/BlackJackRL
Playing Blackjack using Monte Carlo learning with the epsilon greedy strategy.
Jupyter Notebook
Playing Blackjack using Monte Carlo learning with the epsilon greedy strategy.
Jupyter Notebook
Optimal policy compared to any Random policy:
Optimal policy reached by Monte Carlo Method: