← Syed Nazmus Sakib

Teaching

Lecture Notes

Self-contained notes and interactive browser demonstrations covering selected topics in machine learning.

Series Reinforcement LearningFrom MDPs and value functions through PPO and GRPO Notes Reward ModelsPointwise, pairwise, listwise, scalar, ORM, and PRM formulations Notes Self-Supervised LearningConcepts, methods, and selected paper walkthroughs