{
  "id": 10446,
  "url": "https://arxiv.org/abs/2607.13028v1",
  "title": "TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scale",
  "summary": "Training robust autonomous driving agents requires a simulator that is fast enough for reinforcement learning at scale, realistic enough to ground behavior in real-world map structure, and diverse enough to cover the safety-critical long tail that logged data rarely contains. We present TerraZero, a procedural driving simulator and self-play training stack. A configurable C engine runs simulation on the CPU and policy inference on the GPU over a zero-copy path, sustaining 1.3M agent-steps per se",
  "authors": "Zhouchonghao Wu, Akshay Rangesh, Weixin Li, Wei-Jer Chang, Zachary Lee, Tim Wang, Wei Zhan",
  "category": "research",
  "topics": "regulation,agents-autonomy",
  "orgs": null,
  "regions": null,
  "published_at": "2026-07-14T17:59:02.000Z",
  "fetched_at": "2026-07-15T05:10:55.633Z",
  "source_slug": "x-arxiv-cs-ai",
  "source_name": "arXiv cs.AI",
  "source_homepage": "https://arxiv.org/list/cs.AI/recent",
  "ethics_ai_record_url": "https://ethics.ai/record/10446",
  "original_url": "https://arxiv.org/abs/2607.13028v1",
  "evidence_status": "source-only",
  "attribution": "via ethics.ai"
}