03429nam a22004335i 4500001001800000003000900018005001700027007001500044008004100059020001800100024003500118050001400153072001700167072002300184072001600207100007700223245013500300250001800435264005400453300004500507336002600552337002600578338003600604347002400640505063500664520132801299650002202627650002902649650004002678650002202718650002902740650001202769710003402781773002602815776003602841776003602877776003602913856004602949979-8-8688-0273-7DE-He21320251030112628.0cr nn 008mamaa240713s2024    xxu|    s    |||| 0|eng d  a97988688027377 a10.1007/979-8-8688-0273-72doi 4aQ325.5-.7 7aUYQM2bicssc 7aMAT0290002bisacsh 7aUYQM2thema1 aSanghi, Nimish.eauthor.4aut4http://id.loc.gov/vocabulary/relators/aut10aDeep Reinforcement Learning with Pythonh[electronic resource] :bRLHF for Chatbots and Large Language Models /cby Nimish Sanghi.  a2nd ed. 2024. 1aBerkeley, CA :bApress :bImprint: Apress,c2024.  aXXV, 634 p. 204 illus.bonline resource.  atextbtxt2rdacontent  acomputerbc2rdamedia  aonline resourcebcr2rdacarrier  atext filebPDF2rda0 aChapter 1: Introduction to Reinforcement Learning -- Chapter 2: The Foundation – Markov Decision Processes -- Chapter 3: Model Based Approaches -- Chapter 4: Model Free Approaches -- Chapter 5: Function Approximation and Deep Reinforcement Learning -- Chapter 6: Deep Q-Learning (DQN) -- Chapter 7: Improvements to DQN -- Chapter 8: Policy Gradient Algorithms -- Chapter 9: Combining Policy Gradient and Q-Learning -- Chapter 10: Integrated Planning and Learning -- Chapter 11: Proximal Policy Optimization (PPO) and RLHF -- Chapter 12: Introduction to Multi Agent RL (MARL) -- Chapter 13: Additional Topics and Recent Advances.  aGain a theoretical understanding of the most popular libraries in deep reinforcement learning (deep RL). This new edition focuses on the latest advances in deep RL using a learn-by-coding approach, allowing readers to assimilate and replicate the latest research in this field. New agent environments ranging from games, and robotics to finance are explained to help you try different ways to apply reinforcement learning. A chapter on multi-agent reinforcement learning (MARL) covers how multiple agents can be trained, while another chapter focuses on the widely used deep RL algorithm, proximal policy optimization (PPO). You’ll see how reinforcement learning with human feedback (RLHF) has been used to fine-tune Large Language Models (LLMs) to chat and follow instructions. An example of this is the OpenAI ChatGPT offering human like conversational capabilities. You’ll also review the steps for using the code on multiple cloud systems and deploying models on platforms such as Hugging Face Hub. The code is in Jupyter Notebook, which can be run on Google Colab, and other similar deep learning cloud platforms, allowing you to tailor the code to your own needs. Whether it’s for applications in gaming, robotics, or Generative AI, Deep Reinforcement Learning with Python will help keep you ahead of the curve. 0aMachine learning. 0aArtificial intelligence. 0aPython (Computer program language).14aMachine Learning.24aArtificial Intelligence.24aPython.2 aSpringerLink (Online service)0 tSpringer Nature eBook08iPrinted edition:z979886880272008iPrinted edition:z979886880274408iPrinted edition:z979886880855540uhttps://doi.org/10.1007/979-8-8688-0273-7