{
  "type": "book",
  "site": {
    "name": "Kołczan Książek",
    "language": "pl-PL",
    "url": "https://www.kolczanksiazek.pl"
  },
  "formats": "Każda podstrona ma dwie wersje z tymi samymi danymi: JSON (adres strony + .json) i markdown (adres strony + .md). Do każdego `url` w tym dokumencie można dopisać .json albo .md.",
  "title": "A Practical Guide to Reinforcement Learning from Human Feedback. Foundations, aligning large language models, and the evolution of preference-based methods",
  "subtitle": null,
  "slug": "a-practical-guide-to-reinforcement-learning-from-human-feedback-foundations-aligning-large-language-models-and-the-evolution-of-preference-based-methods",
  "url": "https://www.kolczanksiazek.pl/sandip-kulkarni/a-practical-guide-to-reinforcement-learning-from-human-feedback-foundations-aligning-large-language-models-and-the-evolution-of-preference-based-methods",
  "json": "https://www.kolczanksiazek.pl/sandip-kulkarni/a-practical-guide-to-reinforcement-learning-from-human-feedback-foundations-aligning-large-language-models-and-the-evolution-of-preference-based-methods.json",
  "markdown": "https://www.kolczanksiazek.pl/sandip-kulkarni/a-practical-guide-to-reinforcement-learning-from-human-feedback-foundations-aligning-large-language-models-and-the-evolution-of-preference-based-methods.md",
  "authors": [
    {
      "name": "Sandip Kulkarni",
      "slug": "sandip-kulkarni",
      "url": "https://www.kolczanksiazek.pl/sandip-kulkarni"
    }
  ],
  "language": "pl_PL",
  "original_title": null,
  "original_language": null,
  "first_published": null,
  "genres": [],
  "series": [],
  "cover": null,
  "description": "W księgarni informatycznej Helion znajdziesz: A Practical Guide to Reinforcement Learning from Human Feedback. Foundations, aligning large language models, and the evolution of preference-based methods, autor: Sandip Kulkarni, wydawnictwo: Packt Publishing. Produkt dostepny w formacie: Ebook. Pobierz i przeczytaj darmowy fragment.",
  "editions": [
    {
      "title": "A Practical Guide to Reinforcement Learning from Human Feedback. Foundations, aligning large language models, and the evolution of preference-based methods",
      "subtitle": null,
      "url": "https://www.kolczanksiazek.pl/sandip-kulkarni/a-practical-guide-to-reinforcement-learning-from-human-feedback-foundations-aligning-large-language-models-and-the-evolution-of-preference-based-methods/9781835880517",
      "publisher": "Packt Publishing (Z chęcią przeczytam książkę w języku polskim)",
      "publisher_series": [],
      "translators": [],
      "medium": "paper",
      "duration_seconds": null,
      "narrators": [],
      "illustrators": [],
      "cover_artists": [],
      "isbn": "978-18-3588-051-7",
      "pages": 402,
      "published": null,
      "language": "pl_PL",
      "cover": null
    }
  ],
  "other_languages": [],
  "characters": [],
  "chapters": []
}