<urlset xmlns="http://www.sitemaps.org/schemas/sitemap/0.9" xmlns:xhtml="http://www.w3.org/1999/xhtml"><url>
    <loc>https://rlnotes.caomingjun.com/concepts/baseline</loc>
    <lastmod>2024-10-25T09:33:23.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/concepts/basic</loc>
    <lastmod>2024-06-30T13:59:31.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/concepts/behavior-or-target-policy</loc>
    <lastmod>2024-07-01T14:39:29.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/concepts/bellman-equation</loc>
    <lastmod>2024-07-04T14:52:08.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/concepts/ddqn</loc>
    <lastmod>2024-07-25T06:08:30.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/concepts/ebm</loc>
    <lastmod>2025-03-15T15:29:16.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/concepts/epsilon-greedy</loc>
    <lastmod>2024-07-07T04:01:29.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/concepts/experience-replay</loc>
    <lastmod>2024-07-01T14:39:29.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/concepts/</loc>
    <lastmod>2024-06-30T13:59:31.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/concepts/meta-rl</loc>
    <lastmod>2024-07-14T13:29:34.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/concepts/model-based-or-free</loc>
    <lastmod>2024-07-01T14:39:29.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/concepts/noisy-net</loc>
    <lastmod>2024-07-28T15:19:58.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/concepts/online-or-offline</loc>
    <lastmod>2024-07-01T14:39:29.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/concepts/pomdp</loc>
    <lastmod>2024-06-30T13:59:31.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/concepts/popart</loc>
    <lastmod>2024-07-30T10:34:13.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/concepts/recall</loc>
    <lastmod>2024-07-14T13:29:34.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/concepts/reparameterization-trick</loc>
    <lastmod>2025-02-09T09:06:27.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/concepts/semi-mdp</loc>
    <lastmod>2024-06-30T13:59:31.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/concepts/target-network</loc>
    <lastmod>2024-07-01T14:39:29.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/concepts/temporal-difference</loc>
    <lastmod>2024-07-01T14:39:29.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/concepts/value-or-policy-iteration</loc>
    <lastmod>2024-07-01T14:39:29.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/</loc>
    <lastmod>2024-06-21T08:53:05.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/posts/a2c</loc>
    <lastmod>2024-10-25T09:33:23.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/posts/actor-critic</loc>
    <lastmod>2024-10-25T09:33:23.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/posts/dqn</loc>
    <lastmod>2024-07-04T14:55:31.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/posts/dueling-network</loc>
    <lastmod>2024-07-28T10:25:49.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/posts/ppo</loc>
    <lastmod>2025-01-22T08:33:21.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/posts/reinforce</loc>
    <lastmod>2024-10-25T09:33:23.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/posts/sac</loc>
    <lastmod>2025-02-09T09:06:27.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/posts/sarsa</loc>
    <lastmod>2024-07-04T14:52:08.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/posts/trpo</loc>
    <lastmod>2025-01-22T00:42:58.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/tags/model-based</loc>
    <lastmod>2024-10-04T10:02:13.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/tags/model-free</loc>
    <lastmod>2024-10-04T10:02:13.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/tags/off-policy</loc>
    <lastmod>2024-07-07T04:01:29.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/tags/offline</loc>
    <lastmod>2024-07-07T04:01:29.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/tags/on-policy</loc>
    <lastmod>2024-07-07T04:01:29.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/tags/online</loc>
    <lastmod>2024-07-07T04:01:29.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/tags/policy-iteration</loc>
    <lastmod>2024-07-01T14:39:29.000Z</lastmod>
  </url><url>
    <loc>https://rlnotes.caomingjun.com/tags/value-iteration</loc>
    <lastmod>2024-07-01T14:39:29.000Z</lastmod>
  </url></urlset>