FREE delivery to all EXCLUSIVE BOOKS stores nationwide. FREE delivery to your door on all orders over R450. Excludes all international deliveries.

  • Not safe to deliver by Christmas NOTSANTA SAFE
    Reinforcement Learning for Large Language Models

Reinforcement Learning for Large Language Models

Arun Shankar
    Product form
      FORMAT: Paperback / softback

      R 1,628.00 Price and availability exclusive to website

      YOU COULD EARN 1,628 FUTURE RETAIL DISCOUNTS.
      ESTIMATED DELIVERY: Approx. 20 - 30 Business Days
      BUY NOW PAY LATER
      From R 271.33 per month!
      3x monthly payments of R 542.66 with
      4x fortnightly payments of R 407.00 with

      Learn how to train and align large language models with modern reinforcement learning methods using clear explanations and runnable code on free compute.Free with your book: DRM-free PDF version + access to Packt's next-gen Reader*Key FeaturesUnderstand RL for LLMs through intuitive, practical, and mathematical explanationsTrain and align language models using PPO, DPO, and modern efficiency methodsRun every example on free Colab resources with small open modelsPurchase of the print or Kindle book includes a free PDF eBookBook DescriptionReinforcement learning (RL) sits at the heart of aligning modern large language models (LLMs), yet many engineers struggle to learn it because of complex math and expensive infrastructure requirements. This book bridges that gap with clear explanations and hands-on projects that show how to train capable LLMs using free compute and efficient techniques.Start with the mathematical foundations of RL, then progress through supervised fine-tuning (SFT), reward modeling, reinforcement learning from human feedback (RLHF) with proximal policy optimization (PPO), direct preference optimization (DPO), and group relative policy optimization (GRPO). Each concept is reinforced with practical coding exercises and real model outputs, helping you understand the theory and its impact on model behavior.Learn to fine-tune small open models (0.5B–1.5B parameters) with LoRA, mixed-precision training, and memory optimization. Examples are designed for accessible GPU environments, including free Google Colab sessions when available. You'll also explore process reward models, reasoning with GRPO, test-time compute, self-play, agentic systems, and debugging.Written by senior Google Applied AI engineers, this book focuses on practical techniques used in real-world LLM development.By the end of this book, you'll be able to implement, evaluate, and troubleshoot LLM alignment workflows while choosing methods that fit your data and compute budget.*Email sign-up and proof of purchase requiredWhat you will learnUnderstand the RL principles and mathematics behind LLM alignmentBuild complete RLHF pipelines from SFT to policy optimizationApply PPO, DPO, and GRPO in practiceFine-tune small open models using LoRA and memory-efficient techniquesUse process reward models to improve reasoning qualityDiagnose and fix common RL training failuresChoose RL methods based on data and compute constraintsWho this book is forMachine learning engineers, applied researchers, and motivated practitioners who want to use reinforcement learning to improve large language models but have been held back by mathematical complexity or limited compute. Readers should be comfortable with Python and basic ML concepts; no prior reinforcement learning experience is required.

      Format: Paperback / softback CONTRIBUTORS: Arun Shankar EAN: 9781807306793 COUNTRY: United Kingdom PAGES: 320 WEIGHT: HEIGHT: 235 mm
      PUBLISHED BY: Packt Publishing Limited DATE PUBLISHED: 2026-11-30 CITY: GENRE: COMPUTERS / Artificial Intelligence / Natural Language Processing, COMPUTERS / Programming / Algorithms WIDTH: 191 mm SPINE:

      Book Themes:

      Algorithms and data structures, Natural language and machine translation

      Customer Reviews

      Be the first to write a review
      0%
      (0)
      0%
      (0)
      0%
      (0)
      0%
      (0)
      0%
      (0)
      Arun Shankar is a Staff Research Engineer at Google Applied AI, serving as Global Lead Generative AI Blackbelt. He collaborates with Google DeepMind and Google Research teams on AI initiatives involving Gemini, Vertex AI, and agentic systems. Previously, he served as Global Lead AI Architect at AWS, focusing on SageMaker and early Bedrock initiatives. With over 15 years' experience in ML and NLP, Arun has founded companies and held leadership roles across Fortune 500 enterprises and startups. His expertise spans classical computational linguistics, deep learning, and generative AI. Passionate about democratizing AI education, he makes complex concepts accessible through intuitive explanations, practical applications, and mathematical rigor. Mikhail Chertushkin is a Senior ML Engineer at Google Applied AI and a Visiting Professor at Boston University. With over 15 years of experience, he specializes in mathematical optimization, scalable software, and machine learning. He collaborates with Google Research and Gemini Enterprise on agentic AI and model optimization. Starting his career with C++ solutions for complex optimization problems, he transitioned to ML in 2015 and has since led NLP and computer vision teams deploying models at scale. He also designed Boston University's "Advanced ML" and "Deep Learning" courses, helping engineers connect mathematical foundations with real-world AI applications. His mission is to make AI education accessible to engineers everywhere.

      Learn how to train and align large language models with modern reinforcement learning methods using clear explanations and runnable code on free compute.Free with your book: DRM-free PDF version + access to Packt's next-gen Reader*Key FeaturesUnderstand RL for LLMs through intuitive, practical, and mathematical explanationsTrain and align language models using PPO, DPO, and modern efficiency methodsRun every example on free Colab resources with small open modelsPurchase of the print or Kindle book includes a free PDF eBookBook DescriptionReinforcement learning (RL) sits at the heart of aligning modern large language models (LLMs), yet many engineers struggle to learn it because of complex math and expensive infrastructure requirements. This book bridges that gap with clear explanations and hands-on projects that show how to train capable LLMs using free compute and efficient techniques.Start with the mathematical foundations of RL, then progress through supervised fine-tuning (SFT), reward modeling, reinforcement learning from human feedback (RLHF) with proximal policy optimization (PPO), direct preference optimization (DPO), and group relative policy optimization (GRPO). Each concept is reinforced with practical coding exercises and real model outputs, helping you understand the theory and its impact on model behavior.Learn to fine-tune small open models (0.5B–1.5B parameters) with LoRA, mixed-precision training, and memory optimization. Examples are designed for accessible GPU environments, including free Google Colab sessions when available. You'll also explore process reward models, reasoning with GRPO, test-time compute, self-play, agentic systems, and debugging.Written by senior Google Applied AI engineers, this book focuses on practical techniques used in real-world LLM development.By the end of this book, you'll be able to implement, evaluate, and troubleshoot LLM alignment workflows while choosing methods that fit your data and compute budget.*Email sign-up and proof of purchase requiredWhat you will learnUnderstand the RL principles and mathematics behind LLM alignmentBuild complete RLHF pipelines from SFT to policy optimizationApply PPO, DPO, and GRPO in practiceFine-tune small open models using LoRA and memory-efficient techniquesUse process reward models to improve reasoning qualityDiagnose and fix common RL training failuresChoose RL methods based on data and compute constraintsWho this book is forMachine learning engineers, applied researchers, and motivated practitioners who want to use reinforcement learning to improve large language models but have been held back by mathematical complexity or limited compute. Readers should be comfortable with Python and basic ML concepts; no prior reinforcement learning experience is required.

      Format: Paperback / softback CONTRIBUTORS: Arun Shankar EAN: 9781807306793 COUNTRY: United Kingdom PAGES: 320 WEIGHT: HEIGHT: 235 mm
      PUBLISHED BY: Packt Publishing Limited DATE PUBLISHED: 2026-11-30 CITY: GENRE: COMPUTERS / Artificial Intelligence / Natural Language Processing, COMPUTERS / Programming / Algorithms WIDTH: 191 mm SPINE:

      Book Themes:

      Algorithms and data structures, Natural language and machine translation

      Customer Reviews

      Be the first to write a review
      0%
      (0)
      0%
      (0)
      0%
      (0)
      0%
      (0)
      0%
      (0)
      Arun Shankar is a Staff Research Engineer at Google Applied AI, serving as Global Lead Generative AI Blackbelt. He collaborates with Google DeepMind and Google Research teams on AI initiatives involving Gemini, Vertex AI, and agentic systems. Previously, he served as Global Lead AI Architect at AWS, focusing on SageMaker and early Bedrock initiatives. With over 15 years' experience in ML and NLP, Arun has founded companies and held leadership roles across Fortune 500 enterprises and startups. His expertise spans classical computational linguistics, deep learning, and generative AI. Passionate about democratizing AI education, he makes complex concepts accessible through intuitive explanations, practical applications, and mathematical rigor. Mikhail Chertushkin is a Senior ML Engineer at Google Applied AI and a Visiting Professor at Boston University. With over 15 years of experience, he specializes in mathematical optimization, scalable software, and machine learning. He collaborates with Google Research and Gemini Enterprise on agentic AI and model optimization. Starting his career with C++ solutions for complex optimization problems, he transitioned to ML in 2015 and has since led NLP and computer vision teams deploying models at scale. He also designed Boston University's "Advanced ML" and "Deep Learning" courses, helping engineers connect mathematical foundations with real-world AI applications. His mission is to make AI education accessible to engineers everywhere.

      Recently viewed products

      Login

      Forgot your password?

      Don't have an account yet?
      Create account