Topic
Reinforcement Learning
Learn Reinforcement Learning as a connected topic across chapters, concepts, simulations, and interview reasoning.
10 Concepts4 Articles1h 10m
Overview
Learn Reinforcement Learning as a connected topic across chapters, concepts, simulations, and interview reasoning.
How this topic helps
Ai
Llm
Rlhf
Alignment
Learning Path in this Topic
Series that contain articles from Reinforcement Learning. Select a path to filter the article list.
Articles
4 matched articles
Article 1Reinforcement Learning: Agents, Environments, and Rewards in PracticeTLDR: Reinforcement Learning trains agents to make sequences of decisions by learning from rewards and penalties. Unlike supervised learning, RL learns through trial and error rather than labeled exam14 min
Article 2RLHF in Practice: From Human Preferences to Better LLM PoliciesTLDR: Reinforcement Learning from Human Feedback (RLHF) helps align language models with human preferences after pretraining and SFT. The typical pipeline is: collect preference comparisons, train a r12 minArticle 3RLHF Explained: How We Teach AI to Be NiceTLDR: A raw LLM is a super-smart parrot that read the entire internet — including its worst parts. RLHF (Reinforcement Learning from Human Feedback) is the training pipeline that transforms it from a 14 min
Article 4Fine-Tuning LLMs: The Complete Engineer's Guide to SFT, LoRA, and RLHFTLDR: A pretrained LLM is a generalist. Fine-tuning makes it a specialist. Supervised Fine-Tuning (SFT) teaches it your domain's language through labeled examples. LoRA does the same with 99% fewer tr30 min