end-to-end driving 1procedural simulation 1reinforcement learning 1self-play 1self-play reinforcement learning 1simulation 1traffic rule enforcement 1vision alignment 1zero-demonstration training 1zero-shot generalization 1
From the 2 of 3 linked papers with an AI index.
3 papers
cs.CV2026
TerraTransfer: Learning End-to-End Driving Policies Without Expert Demonstrations
Zikang Xiong, Weixin Li, Zhouchonghao Wu +6
The paper proposes a method to train end-to-end autonomous driving policies without expert demonstrations by pretraining a policy via self‑play in a fast vectorized simulator and t…
cs.LG2026
TerraZero: Procedural Driving Simulation for Zero-Demonstration Self-Play at Scale
Zhouchonghao Wu, Akshay Rangesh, Weixin Li +5
TerraZero is a procedural driving simulator that enables large-scale, zero‑demonstration self‑play reinforcement learning for autonomous driving, achieving high simulation speed an…
cs.LG2026
SPACeR: Self-Play Anchoring with Centralized Reference Models
Wei-Jer Chang, Akshay Rangesh, Kevin Joseph +4
Developing autonomous vehicles (AVs) requires not only safety and efficiency, but also realistic, human-like behaviors that are socially aware and predictable. Achieving this requi…