CoIRL-AD：面向自动驾驶的潜在世界模型中的协作-竞争模仿-强化学习
CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous Driving
AI总结：
提出CoIRL-AD框架，通过解耦模仿学习与强化学习、利用潜在世界模型进行长时程奖励估计以及引入竞争机制，在离线训练中提升自动驾驶的鲁棒性，尤其在跨城市泛化和长尾场景中表现优异。
摘要：
基于模仿学习（IL）训练的端到端自动驾驶模型通常泛化能力较差，尤其是在专家演示稀疏的长尾场景中。强化学习（RL）可以提供互补的任务级监督，但在没有交互模拟器的离线设置中，将RL应用于真实世界的自动驾驶具有挑战性，因为数据集主要由专家动作主导，行为多样性有限。我们提出CoIRL-AD，一个竞争性的双策略框架，在统一的离线训练机制下整合IL和RL。CoIRL-AD将模仿和奖励优化解耦到不同的智能体中，以缓解目标冲突，使用想象的未来轨迹进行长时程奖励估计，并引入竞争机制，选择性地传递有益行为，同时使RL保持与专家驾驶行为一致。在nuScenes基准上的实验表明，CoIRL-AD在强IL基线上持续提升鲁棒性，尤其在跨城市泛化和长尾场景中取得了显著改进。代码可在以下网址获取：this https URL。
英文摘要：
End-to-end autonomous driving models trained with imitation learning (IL) often generalize poorly, particularly in long-tail scenarios where expert demonstrations are sparse. Reinforcement learning (RL) can provide complementary task-level supervision, but applying RL to real-world autonomous driving is challenging in offline settings without interactive simulators, where datasets are dominated by expert actions and provide limited behavioral diversity. We propose CoIRL-AD, a competitive dual-policy framework that integrates IL and RL under a unified offline training regime. CoIRL-AD decouples imitation and reward optimization into separate actors to alleviate objective conflicts, uses imagined future rollouts for long-horizon reward estimation, and introduces a competition mechanism that selectively transfers beneficial behaviors while keeping RL anchored to expert-like driving. Experiments on the nuScenes benchmark show that CoIRL-AD consistently improves robustness over strong IL-based baselines, with especially large gains in cross-city generalization and long-tail scenarios. Code is available at: https://github.com/SEU-zxj/CoIRL-AD.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
