Developping an ideal policy for playing a simplified game of blackjack using 3 different methods:
Monte-Carlo
TD Learning (SARSA)
Q-Learning
comparison of algorithms:
view here: https://nbviewer.jupyter.org/github/AmlraEF/easyblackjack/blob/main/easy21mod.ipynb
Developping an ideal policy for playing a simplified game of blackjack using 3 different methods:
Monte-Carlo
TD Learning (SARSA)
Q-Learning
comparison of algorithms:
view here: https://nbviewer.jupyter.org/github/AmlraEF/easyblackjack/blob/main/easy21mod.ipynb