Andrew likes math
Just for fun to share anything
miércoles, 29 de abril de 2026
jueves, 19 de febrero de 2026
2026 — Year of the Horse
The Year of the Horse (2026) begins on:
February 17, 2026
and ends on:
February 5, 2027
The Chinese zodiac follows the lunar calendar, so it does not start on January 1.
🌟 Symbolic Meaning of a Fire Horse Year
Traditionally associated with:
-
Fast progress
-
Innovation
-
High energy
-
Risk-taking
-
Big public movements
It is considered a year of motion and acceleration, not stagnation.
miércoles, 28 de enero de 2026
Reinforce Learning
Reinforcement learning (RL) is a branch of machine learning where an agent learns to make decisions by interacting with an environment to maximize cumulative reward. Its roots trace back to early work in psychology and control theory, but the modern framework began taking shape in the 1980s and 1990s with contributions from researchers like Richard Sutton and Andrew Barto. A major milestone came in 2013 when DeepMind (co-founded by Demis Hassabis) introduced Deep Q-Networks (DQN), which combined deep neural networks with Q-learning to achieve human-level performance on Atari games. This breakthrough catalyzed the field of deep reinforcement learning. Subsequent achievements—such as AlphaGo (2016), AlphaZero (2017), and MuZero (2019)—demonstrated RL’s power in complex domains like Go, chess, and planning without explicit environmental models.
