SOURCE-LINKED INTELLIGENCE

CounterPlay: Counterfactual Post-Training for Self-Play Driving Policies

arXiv · AI, language, vision and robotics · article · Sep 18, 2026 · UTC

Self-play in high-throughput simulators yields driving policies with robust closed-loop performance, but improvement per unit of simulation diminishes as training scales. Policies learn to handle common situations early, while further rollouts repeatedly encounter unresolved failures. Post-training offers an opportunity to target these failures, but existing methods primarily evaluate alternative actions or continuations at visited states, although successful recovery may require changing driving style earlier. We propose CounterPlay, a counterfactual self-play post-training approach that back

Read original source ↗ Open in workspace

recordType

paper

region

Global