Skip to content

Latest commit

 

History

History
2 lines (2 loc) · 292 Bytes

File metadata and controls

2 lines (2 loc) · 292 Bytes

Monte-Carlo-Control-to-solve-Blackjack

Interacting with the blackjack environment from OpenAI gym. We will write our own Monte Carlo Control implementation to find an optimal policy to solving blackjack. The code and theory has been learnt from Udacity Deep Reinforcement Learning course.