Topics
Learning Reinforcement Learning
01Introduction to Reinforcement Learning
02From Minimax to Reinforcement Learning : Why RL wins at Tic-Tac-Toe ?
03Multi-armed Bandits : Introducing evaluative aspect to RL
+ 5 more chapters
Explore Series
Building Language Models from Scratch
01From Zero to 250M: How I Built the STE Dataset to Train a Tiny LLM from Scratch
02DotLM-165M: How I trained a 165M parameter language model from scratch
Explore Series
RL from Scratch
01AresSim - Mars Survival Simulation & RL Environment
Explore Series
Reinforcement Learning
1 topic • 8 postsMarkov Decision Processes, dynamic programming, value iteration, bandit algorithms, policy networks, and control.
LLMs
11 topics • 3 postsLarge Language Models, pretraining architectures, reasoning models, SFT, DPO, and context engineering.
Generative AI
12 topics • 3 postsText generation models, synthetic datasets, instruction tuning, RAG systems, and generative architectures.