Training a PPO Agent with Grok to Play a Self-Built Game
tetsuoai · x · 2026-09-01
The author used Grok to build a browser game called Roofline and then trained a PPO agent using Grok to play the live page. The best recorded run achieved a score of 39,359, covering 4,924 meters with a combo of 117. The game is available to play online.
Related event: Developer Uses Grok to Build a Game and Train a PPO Agent to Play It(3 posts)→
More from coding & agent
- Claude-written test harness let 31KB fake archives land on a real backup server — Grimmoner · 2026-10-18
- Matt Pocock's pre-commit hook caps agent-written files at 5,000 tokens — mattpocockuk · 2026-10-18
- Backups silently failed for 10 days: three monitoring blind spots lined up — Grimmoner · 2026-10-18
- Author Laurence Moroney: write your ugly first draft yourself, then let an LLM edit it — lmoroney · 2026-10-18
- Open-weight TYGER speech decision model makes 80ms turn-taking calls for full-duplex voice agents — solyarisoftware · 2026-10-18
- Devs: Opus 5.5 on medium beats Opus on max — eyishazyer · 2026-10-18