https://styleofwong.cn/tags/reinforcement-learning/Recent content in Reinforcement Learning on 王辉赳的小站https://styleofwong.cn/apple-touch-icon.pnghttps://styleofwong.cn/apple-touch-icon.pngHugozh-CNSun, 28 Jun 2026 18:00:00 +0800https://styleofwong.cn/posts/reinforcement-learning-intro/Sun, 28 Jun 2026 18:00:00 +0800https://styleofwong.cn/posts/reinforcement-learning-intro/强化学习是让 AI 学会『在试错中成长』的范式。本文从最核心的直觉出发,讲清楚 MDP、贝尔曼方程、Q-Learning,并附一个可运行的 Python 示例。