Building a Game with Grok and Training a PPO Agent: Open Source Project
tetsuoai · x · 2026-09-02
The author used Grok to build the browser game Roofline and trained a PPO agent on a headless port of the game. The agent plays live on the website as 'Tetsuo MLBot', achieving a high score of 39,359. The project is open source with code and weights available for local training or direct deployment. The Python sim matches live physics at 120 Hz and includes optimizations like net injection to reduce input latency.
Related event: Developer Uses Grok to Build a Game and Train a PPO Agent to Play It(3 posts)→
More from coding & agent
- Anthropic borrows lawyers' ethics for Claude agents that closed 186 deals with no human approval — rohanpaul_ai · 2026-10-18
- Prompt injection via email can hijack your AI agent — jev-guard adds risk-scored guards — sujingshen · 2026-10-18
- 14-Agent AI Film Pipeline on One RTX 5090: Fixing Cut Defects Between Clips — developervkmp · 2026-10-18
- Meta paper introduces "agent plasticity": best-performing agent isn't the most efficient learner — rohanpaul_ai · 2026-10-18
- Dev ships a bushfire prediction platform in a weekend with frontier models — CtrlAltDwayne · 2026-10-18
- 10 open-source GitHub repos that let AI agents control your phone, from Open-AutoGLM to mobile-use — victor_explore · 2026-10-18