<?xml version="1.0" encoding="utf-8" standalone="yes"?><rss version="2.0" xmlns:atom="http://www.w3.org/2005/Atom" xmlns:content="http://purl.org/rss/1.0/modules/content/"><channel><title>Posts on Wang Huijiu's Site</title><link>https://styleofwong.cn/en/posts/</link><description>Recent content in Posts on Wang Huijiu's Site</description><image><title>Wang Huijiu's Site</title><url>https://styleofwong.cn/apple-touch-icon.png</url><link>https://styleofwong.cn/apple-touch-icon.png</link></image><generator>Hugo</generator><language>en-US</language><lastBuildDate>Mon, 13 Jul 2026 00:01:00 +0800</lastBuildDate><atom:link href="https://styleofwong.cn/en/posts/index.xml" rel="self" type="application/rss+xml"/><item><title>Site Infrastructure Update: Analytics, ICP Filing, and Caching</title><link>https://styleofwong.cn/en/posts/site-infrastructure-update-20260713/</link><pubDate>Mon, 13 Jul 2026 00:01:00 +0800</pubDate><guid>https://styleofwong.cn/en/posts/site-infrastructure-update-20260713/</guid><description>Today I added domestic and international traffic analytics, displayed filing information, and reorganized the static asset caching strategy for this site.</description></item><item><title>Taming Balatro: Pushing White Stake Clear Rate to 99% with Reinforcement Learning</title><link>https://styleofwong.cn/en/posts/balatro-rl-design/</link><pubDate>Sun, 28 Jun 2026 19:30:00 +0800</pubDate><guid>https://styleofwong.cn/en/posts/balatro-rl-design/</guid><description>If we want to achieve a 99% Ante 8 clear rate on Balatro White Stake, how should the RL algorithm be designed? This article presents a concrete technical blueprint from game-mechanics modeling, state/action spaces, reward shaping to algorithm selection, and explains why pure PPO won&amp;rsquo;t work and why a hybrid MCTS+RL architecture is necessary.</description></item><item><title>From AlphaZero to Dota 2: Three Bottlenecks in Reinforcement Learning and How They Were Broken</title><link>https://styleofwong.cn/en/posts/rl-breakthroughs-alphazero-dota/</link><pubDate>Sun, 28 Jun 2026 19:00:00 +0800</pubDate><guid>https://styleofwong.cn/en/posts/rl-breakthroughs-alphazero-dota/</guid><description>AlphaZero and OpenAI Five are two milestones in reinforcement learning. What walls did each of them hit, and what engineering and algorithmic innovations knocked those walls down? This article dissects them with a pyramid structure: three shared bottlenecks — data, stability, and scale — and how each project broke through them.</description></item><item><title>Introduction to Reinforcement Learning: From Intuition to Q-Learning</title><link>https://styleofwong.cn/en/posts/reinforcement-learning-intro/</link><pubDate>Sun, 28 Jun 2026 18:00:00 +0800</pubDate><guid>https://styleofwong.cn/en/posts/reinforcement-learning-intro/</guid><description>Reinforcement learning is the paradigm that lets AI learn to &amp;ldquo;grow through trial and error&amp;rdquo;. Starting from the most fundamental intuition, this article clearly explains MDP, the Bellman equation, and Q-Learning, and includes a runnable Python example.</description></item><item><title>Hello, World — The Blog Is Live</title><link>https://styleofwong.cn/en/posts/hello-world/</link><pubDate>Sun, 28 Jun 2026 10:00:00 +0800</pubDate><guid>https://styleofwong.cn/en/posts/hello-world/</guid><description>This is the first post on Huijiu Wang&amp;rsquo;s personal blog, marking the birth of this little site.</description></item></channel></rss>