<?xml version="1.0" encoding="UTF-8"?>
<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:news="http://www.google.com/schemas/sitemap-news/0.9" xmlns:xhtml="http://www.w3.org/1999/xhtml" xmlns:image="http://www.google.com/schemas/sitemap-image/1.1" xmlns:video="http://www.google.com/schemas/sitemap-video/1.1">
    
  <url>
    <loc>https://agent-rl.tacetai.com</loc>
    <lastmod>2026-10-20T20:44:07.226Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/chapters/00-notation</loc>
    <lastmod>2026-10-20T20:44:07.230Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/chapters/01-introduction</loc>
    <lastmod>2026-10-20T20:44:07.229Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/chapters/02-rl-fundamentals</loc>
    <lastmod>2026-10-20T20:44:07.225Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/chapters/03-language-models-as-policies</loc>
    <lastmod>2026-10-20T20:43:56.512Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/chapters/04-environments-and-tools</loc>
    <lastmod>2026-10-20T20:43:56.506Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/chapters/05-trajectories-and-templates</loc>
    <lastmod>2026-10-20T20:43:56.497Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/chapters/06-policy-gradient</loc>
    <lastmod>2026-10-20T20:43:56.503Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/chapters/07-advantages-and-credit</loc>
    <lastmod>2026-10-20T20:43:56.504Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/chapters/08-ppo</loc>
    <lastmod>2026-10-20T20:43:56.470Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/chapters/09-grpo-and-variants</loc>
    <lastmod>2026-10-20T20:43:56.501Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/chapters/10-kl-entropy-regularization</loc>
    <lastmod>2026-10-20T20:43:56.515Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/chapters/11-rewards-and-verifiers</loc>
    <lastmod>2026-10-20T20:43:56.513Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/chapters/12-multi-turn-and-long-horizons</loc>
    <lastmod>2026-10-20T20:43:56.508Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/chapters/13-rollout-systems</loc>
    <lastmod>2026-10-20T20:43:56.518Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/chapters/14-scaling-and-efficiency</loc>
    <lastmod>2026-10-20T20:43:56.514Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/chapters/15-sft-and-rejection-sampling</loc>
    <lastmod>2026-10-20T20:43:56.509Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/chapters/16-distillation</loc>
    <lastmod>2026-10-20T20:43:56.507Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/chapters/17-evaluation</loc>
    <lastmod>2026-10-20T20:43:56.469Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/chapters/18-debugging-rl-runs</loc>
    <lastmod>2026-10-20T20:43:56.506Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/chapters/19-capstone</loc>
    <lastmod>2026-10-20T20:43:56.505Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/chapters/20-frontier</loc>
    <lastmod>2026-10-20T20:43:56.466Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/chapters/A-math</loc>
    <lastmod>2026-10-20T20:43:56.514Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/chapters/B-design-review</loc>
    <lastmod>2026-10-20T20:43:56.507Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/editorial-guide</loc>
    <lastmod>2026-10-20T20:43:56.502Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/labs/README</loc>
    <lastmod>2026-10-20T20:43:56.504Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/library</loc>
    <lastmod>2026-10-20T20:43:56.503Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/sources</loc>
    <lastmod>2026-10-20T20:43:56.463Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/README</loc>
    <lastmod>2026-10-20T22:30:26.637Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/chapters/00-notation</loc>
    <lastmod>2026-10-20T22:30:26.653Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/chapters/01-introduction</loc>
    <lastmod>2026-10-20T22:30:26.631Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/chapters/02-rl-fundamentals</loc>
    <lastmod>2026-10-20T22:30:26.644Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/chapters/03-language-models-as-policies</loc>
    <lastmod>2026-10-20T22:30:26.644Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/chapters/04-environments-and-tools</loc>
    <lastmod>2026-10-20T22:30:26.639Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/chapters/05-trajectories-and-templates</loc>
    <lastmod>2026-10-20T22:30:26.633Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/chapters/06-policy-gradient</loc>
    <lastmod>2026-10-20T22:30:26.643Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/chapters/07-advantages-and-credit</loc>
    <lastmod>2026-10-20T22:30:26.640Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/chapters/08-ppo</loc>
    <lastmod>2026-10-20T22:30:26.660Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/chapters/09-grpo-and-variants</loc>
    <lastmod>2026-10-20T22:30:26.635Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/chapters/10-kl-entropy-regularization</loc>
    <lastmod>2026-10-20T22:30:26.656Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/chapters/11-rewards-and-verifiers</loc>
    <lastmod>2026-10-20T22:30:26.661Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/chapters/12-multi-turn-and-long-horizons</loc>
    <lastmod>2026-10-20T22:30:26.642Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/chapters/13-rollout-systems</loc>
    <lastmod>2026-10-20T22:30:26.642Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/chapters/14-scaling-and-efficiency</loc>
    <lastmod>2026-10-20T22:30:26.641Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/chapters/15-sft-and-rejection-sampling</loc>
    <lastmod>2026-10-20T22:30:26.633Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/chapters/16-distillation</loc>
    <lastmod>2026-10-20T22:30:26.640Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/chapters/17-evaluation</loc>
    <lastmod>2026-10-20T22:30:26.634Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/chapters/18-debugging-rl-runs</loc>
    <lastmod>2026-10-20T22:30:26.638Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/chapters/19-capstone</loc>
    <lastmod>2026-10-20T22:30:26.664Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/chapters/20-frontier</loc>
    <lastmod>2026-10-20T22:30:26.662Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/chapters/A-math</loc>
    <lastmod>2026-10-20T22:30:26.632Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/chapters/B-design-review</loc>
    <lastmod>2026-10-20T22:30:26.638Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/glossary</loc>
    <lastmod>2026-10-20T22:30:26.659Z</lastmod>
  </url>

  <url>
    <loc>https://agent-rl.tacetai.com/tutorial/zh/labs/README</loc>
    <lastmod>2026-10-20T22:30:26.663Z</lastmod>
  </url>
</urlset>