TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scale
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 second on a single server-grade GPU, far faster than existing object-level simulators, while keeping f
Lineage graph
Paper → model → repo connections mined from source citations (Tier-1 exact match).
Why these links exist
Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.
- PossiblePossibly related (embedding) · 55%autowarefoundation/auto_e2e →
- PossiblePossibly related (embedding) · 54%carla-simulator/carla →
- PossiblePossibly related (embedding) · 53%grandgaming9321-prog/reality-engine →
- PossiblePossibly related (embedding) · 52%horizonfps/project-lunar →
- PossiblePossibly related (embedding) · 52%gpustack/gpustack →
- LinkedLinked via arxiv author · 85%Zhouchonghao Wu →
“TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scale”
- LinkedLinked via arxiv author · 85%Akshay Rangesh →
“TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scale”
- LinkedLinked via arxiv author · 85%Weixin Li →
“TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scale”