Junior data scientist passionate about machine learning.
This project showcases how to use DDQN algorithm with action masking to train an agent how to play the game and win against fixed policies.
Link: https://github.com/Aff54/Reinforcement-learning-applied-to-Liar-s-dice.
In this repo, I put my answers to the first four advent of code 2025 problems (part 1 and 2) with explanations.
Link: https://github.com/Aff54/advent-of-code-2025-days-1-4