[{"data":1,"prerenderedAt":88},["ShallowReactive",2],{"wiki-reinforcement-learning":3,"wiki-summaries":51},{"id":4,"title":5,"body":6,"category":36,"description":37,"extension":38,"meta":39,"navigation":40,"path":41,"related":42,"seo":43,"slug":44,"stem":45,"tags":46,"updated":49,"__hash__":50},"wiki\u002Fwiki\u002Freinforcement-learning.md","强化学习",{"type":7,"value":8,"toc":32},"minimark",[9,13,16],[10,11,12],"p",{},"强化学习是我后续准备系统整理的重要方向。",[10,14,15],{},"当前先记录一个简要框架，后续会逐步扩展为更完整的学习笔记，包括：",[17,18,19,23,26,29],"ul",{},[20,21,22],"li",{},"Agent、环境、状态、动作、奖励",[20,24,25],{},"值函数和策略的基本理解",[20,27,28],{},"DQN、PPO 等常见算法",[20,30,31],{},"强化学习和工程控制问题的结合",{"title":33,"searchDepth":34,"depth":34,"links":35},"",2,[],"算法学习","记录强化学习的基础框架、常见算法路线以及后续学习重点。","md",{},true,"\u002Fwiki\u002Freinforcement-learning",[],{"title":5,"description":37},"reinforcement-learning","wiki\u002Freinforcement-learning",[5,47,48],"RL","算法","2026-06-07","6tJWCreCz6CguUfW0iPAowhqMpRrgMOlo_ESwNYLl9M",[52,62,70,77,86],{"title":53,"slug":54,"description":55,"category":56,"tags":57,"updated":61},"C++探索之旅","cpp","整理 C++ 在工程开发中的常用语法、调试经验和项目实践记录。","编程语言",[58,59,60],"C++","工程开发","学习笔记","2026-08-09",{"title":63,"slug":64,"description":65,"category":66,"tags":67,"updated":49},"Fedora","fedora","记录 Fedora 的安装、环境配置、软件管理以及日常使用问题。","系统环境",[63,68,69],"Linux","环境配置",{"title":71,"slug":72,"description":73,"category":36,"tags":74,"updated":49},"MoE","moe","记录 Mixture of Experts 的基础概念、常见结构和后续工程实践方向。",[71,75,76],"深度学习","模型结构",{"title":78,"slug":79,"description":80,"category":81,"tags":82,"updated":49},"Nuxt 博客项目结构","nuxt-blog-project-structure","记录当前个人博客项目的目录设计、页面结构和内容组织方式。","前端项目",[83,84,85],"Nuxt","博客搭建","项目结构",{"title":5,"slug":44,"description":37,"category":36,"tags":87,"updated":49},[5,47,48],1793262929591]