https://zzefone.github.io/myblog/tags/ppo/Recent content in PPO on WANG Zhaofeng · Course PortfolioHugoenMon, 19 Oct 2026 00:00:00 +0000https://zzefone.github.io/myblog/posts/hci-lab-1-ml-agents/Mon, 12 Oct 2026 00:00:00 +0000https://zzefone.github.io/myblog/posts/hci-lab-1-ml-agents/<p>Signal Chase starts with a simple task: move a cyan sphere towards a gold target. The extension makes the target move and reflect from the platform edges. Both tasks use learned PPO policies, not a scripted chasing rule.</p> <img src="https://zzefone.github.io/myblog/images/hci/lab-1-ml-agents/chase-runtime.png" alt="A cyan learning agent and gold moving target on the Signal Chase platform, rendered from the running Windows player."> <p><em>Runtime camera capture of the moving-target task. The desktop control overlay is not included in this capture.</em></p>