Keras Reinforcement Learning Projects
by Giuseppe Ciaburro, Sudharsan Ravichandiran, Suriyadeepan Ramamoorthy
Historical background
According to some, the historical origins of Monte Carlo methods could be dated back to 1700 D.C., well before the advent of computers. In 1777, the French mathematician George Louis Leclerc de Buffon describes in his work, Essai d'arithmetique morale, an experiment to estimate value through a random simulation based on the launch of a needle, obtaining a result of good numerical precision for the time. Suppose we have a floor made of parallel strips of wood, each of the same width and greater than the length of a needle, and we drop that needle onto the floor. What is the probability that the needle will land on a line between two strips? In the following diagram, two possible events are shown:
Needle 1 does not lie ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access