I’m deeply excited about building AI algorithms!

You can check some of my open source implementations right there:

• MuZero: The new sister of AlphaZero is planning moves using a model of the environment learned in an unsupervised manner.
• AlphaRL: My attempt to build a Reinforcement Learning framework from scratch!
• Expectation-Maximisation: I’ll keep it short. K-means + probability ≈ EM.
• Kohonen: A self-organizing map: a kind of artificial neural network trained in a unsupervised way.
• Alpha-Beta: Look at my smart board game player :)
• Q-Learning: Learns that Q-value. In quest of the optimal policy.
• Perceptron: My first neural network ever, cool!