4/ š We introduce NO data Map-based self-play for Autonomous Driving (NOMAD), which adapts a driving policy to a new city using only the city's lane-level map + meta info. The policy is trained via KL-regularized self-play in a target-city simulator.
8/ :heart: Thanks to my amazing collaborators @saeedrmd.bsky.social , @daphne-cornelisse.bsky.social @bidiptas13.bsky.social @alexdgoldie.bsky.social @jfoerst.bsky.social @shimon8282.bsky.social. Thanks to all colleagues for the helpful discussions.
If youāre into AVs / RL, weād love your thoughts!
6/ š¬ We also analyze:
ā¢ role of behavioral priors
ā¢ necessity of target-city maps
ā¢ comparison to methods that do use target-city demos
ā¢ generalization across cities
ā¢ sensitivity to KL strength
ā¢ evaluation under non-self-play agents
ā¢ effect of map mirroring
7/ š® NOMAD substantially narrows cross-city generalization gaps, supporting scalable deployment of autonomous driving systems across diverse environments and highlighting the promise of self-play MARL for improving safety and robustness.
Paper: arxiv.org/abs/2602.15891