Complex AI and statistics made easy
We aim to break down the most complex concepts into intutive examples to help you go further and come up with new ideas!
View all our posts
Index
Optimal control and dynamic programming:
- Value Estimation with Monte Carlo Methods: Learning from Experience
- Understanding the Value Function in Reinforcement Learning: A Corridor Example
- Finding a Reinforcement Learning Policy with a Markov Decision Process: Generalized Policy Iteration (GPI)
Statistics and Probability:
- Bayes’ Theorem and its Applications to Classification and Sequence Models
- Intuition Behind the Birthday Paradox
Featured post
Featured post
Finding a Reinforcement Learning Policy with a Markov Decision Process: Generalized Policy Iteration (GPI)
March 31, 2025 | by Romeo