René's URL Explorer Experiment


Title: 第二十八章:强化学习与RLHF - AI学习笔记

Description: 深入学习强化学习原理与RLHF技术,从马尔可夫决策到大语言模型的人类反馈优化。

direct link

Domain: jacksoncode.github.io

Links:

AI学习笔记 https://jacksoncode.github.io/tutorials/index.html
首页https://jacksoncode.github.io/tutorials/index.html
AI笔记目录https://jacksoncode.github.io/tutorials/ai-notes/index.html
https://github.com/jacksoncode
28.1 强化学习基础概念https://jacksoncode.github.io/tutorials/ai-notes/ch28.html#section1
28.2 核心算法:Q-Learning与策略梯度https://jacksoncode.github.io/tutorials/ai-notes/ch28.html#section2
28.3 深度强化学习https://jacksoncode.github.io/tutorials/ai-notes/ch28.html#section3
28.4 RLHF详解https://jacksoncode.github.io/tutorials/ai-notes/ch28.html#section4
28.5 奖励模型训练https://jacksoncode.github.io/tutorials/ai-notes/ch28.html#section5
28.6 PPO在大语言模型中的应用https://jacksoncode.github.io/tutorials/ai-notes/ch28.html#section6
28.7 DPO与RLHF的对比https://jacksoncode.github.io/tutorials/ai-notes/ch28.html#section7
28.8 动手实践:TRL库https://jacksoncode.github.io/tutorials/ai-notes/ch28.html#section8
上一章:大语言模型微调 https://jacksoncode.github.io/tutorials/ai-notes/ch27.html
下一章:大语言模型评估 https://jacksoncode.github.io/tutorials/ai-notes/ch29.html

Viewport: width=device-width, initial-scale=1.0


URLs of crawlers that visited me.