按年被提到
20252025 · 1 次2026
强化学习与智能体›博弈与游戏 AI·arXiv:2502.03349 · cs.LG

Robust Autonomy Emerges from Self-Play

Marco Cusumano-Towner, David Hafner, Alex Hertzberg, Brody Huval, Aleksei Petrenko, Eugene Vinitsky, Erik Wijmans, Taylor Killian, Stuart Bowers, Ozan Sener, Philipp Krähenbühl, Vladlen Koltun · 2025
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 2 人首次 2025-02-07 · 最近 2026-02-13
2不同的人
2活跃月份
2讨论串
6被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Self-play has powered breakthroughs in two-player and multi-player games. Here we show that self-play is a surprisingly effective strategy in another domain. We show that robust and naturalistic driving emerges entirely from self-play in simulation at unprecedented scale -- 1.6~billion~km of driving. This is enabled by Gigaflow, a batched simulator that can synthesize and train on 42 years of subjective driving experience per hour on a single 8-GPU node. The resulting policy achieves state-of-the-art performance on three independent autonomous driving benchmarks. The policy outperforms the prior state of the art when tested on recorded real-world scenarios, amidst human drivers, without ever seeing human data during training. The policy is realistic when assessed against human references and achieves unprecedented robustness, averaging 17.5 years of continuous driving between incidents in simulation.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及
评论rangestransform · 2026-02

““Cruise” is still churning out good tech, they gave a talk recently about using a lightweight [1] type of planner to train an end to end VLA style planner [1] https://arxiv.org/abs/2502.03349”

Beginning autonomous operations with the 6th-generation Waymo Driver原评论 ↗
被提交为 story · 1 次