Upload index.html

index.html

@@ -503,7 +503,7 @@
     <h2><span class="sec-num">03</span>Demonstration</h2>
     <div class="section-divider"></div>
 
-    <p>We have developed a Python normal AI bot that can beat OpenRA easy AI bot. The environment code is on <a href="https://github.com/yxc20089/OpenRA-RL" target="_blank">GitHub (OpenRA-RL)</a> and also deployed as a <a href="https://huggingface.co/spaces/openra-rl/openra-rl-challenge" target="_blank">live HuggingFace Space</a>; the training/challenge code is at <a href="https://github.com/huixu11/openra-rl-challenge" target="_blank">GitHub (openra-rl-challenge)</a>. The replay can be watched <a href="https://youtu.be/YaO-KyHiXfo" target="_blank">on YouTube</a>.</p>
+    <p>We have developed a Python normal AI bot that can beat OpenRA easy AI bot. The environment code is on <a href="https://github.com/yxc20089/OpenRA-RL" target="_blank">GitHub (OpenRA-RL)</a> and also deployed as a <a href="https://huggingface.co/spaces/openra-rl/openra-rl" target="_blank">live HuggingFace Space</a>; the training/challenge code is at <a href="https://github.com/huixu11/openra-rl-challenge" target="_blank">GitHub (openra-rl-challenge)</a>. The replay can be watched <a href="https://youtu.be/YaO-KyHiXfo" target="_blank">on YouTube</a>.</p>
 
     <p>To exercise the platform end-to-end through the OpenEnv interface, we deploy Qwen3 32B served locally via Ollama as an LLM agent playing the Allied faction against the built-in Beginner AI on a 128×128 map. The agent receives structured game-state observations as tool responses and issues actions through the MCP tools. We run five episodes under two timing regimes: <strong>Games 1–2 use a 30-minute time limit, while Games 3–5 use a 5-minute limit.</strong></p>
 
@@ -655,7 +655,7 @@ env.close()</code></pre>
 </main>
 
 <footer>
-  <p>OpenRA-RL · April 2026 · <a href="https://huggingface.co/openenv" target="_blank">OpenEnv Hub</a> · <a href="https://huggingface.co/spaces/openra-rl/openra-rl-challenge" target="_blank">HF Space</a> · <a href="https://github.com/yxc20089/OpenRA-RL" target="_blank">Environment (GitHub)</a> · <a href="https://github.com/huixu11/openra-rl-challenge" target="_blank">Training (GitHub)</a> · <a href="_OpenENV_Blog__OpenRA_RL.pdf" target="_blank">PDF</a></p>
+  <p>OpenRA-RL · April 2026 · <a href="https://huggingface.co/openenv" target="_blank">OpenEnv Hub</a> · <a href="https://huggingface.co/spaces/openra-rl/openra-rl" target="_blank">HF Space</a> · <a href="https://github.com/yxc20089/OpenRA-RL" target="_blank">Environment (GitHub)</a> · <a href="https://github.com/huixu11/openra-rl-challenge" target="_blank">Training (GitHub)</a> · <a href="_OpenENV_Blog__OpenRA_RL.pdf" target="_blank">PDF</a></p>
   <p style="margin-top:8px;opacity:0.5;">Xiaochuang Yuan, Hui Xu, Yiyu Tian, Siqi Zhang, Ruiyue Wang, Kaiser Sun</p>
 </footer>