Reinforcement Learning

Learning from reward rather than labels. Powerful in games, rare in normal data science work, and this explains why.

3 articles, newest first.

• Reinforcement Learning · Jun 4, 2026 · 6 min Bandits are the reinforcement learning you will actually use Full RL rarely survives contact with a business problem. Multi-armed bandits do: the same explore-exploit trade, without the state, the simulator or the reward engineering.
• Generative models and LLMs · Part 28 of 33 · 7 min How a model gets trained, from pretraining to RLHF The three stages that turn raw text into a chat assistant, what each one actually changes about the model, and why the base model and the assistant are different things.
• Generative models and LLMs · Part 33 of 33 · 8 min Reinforcement learning, and what AlphaGo taught Learning from consequences instead of answers: agent, reward, and the credit assignment problem — plus an honest account of why reinforcement learning is rare in normal data work.