arXiv cs.AI· Mahmoud Selim, Cristina Cipriani, Karl Henrik Johansson·· 3 天前AI 评分23
面向自动驾驶的交互约束离线强化学习框架 ICDP
Beyond Policy Support: Interaction Constrained Offline Reinforcement Learning for Autonomous Driving
AI 导读
针对离线强化学习在自动驾驶中面临的交互分布偏移（IDS）问题，研究者提出交互约束驾驶策略框架 ICDP，将联合支撑退化精确分解为 ego 支撑与残差交互支撑两部分，并通过对比密度比估计恢复后者，无需联合密度建模、周围智能体预测或反应式模拟器与世界模型 rollout。
正文 · 原文
Abstract:Offline reinforcement learning enables reward-driven policy improvement from fixed datasets without requiring online exploration, making it particularly attractive in safety-critical domains. A central challenge, however, is distribution shift: policy optimization may favor actions that are weakly supported by the offline data, rendering value estimates unreliable. Existing approaches primarily control this shift in the policy's own action space. In interactive environments such as autonomous driving, this can be insufficient: a candidate ego trajectory may remain well supported under the marginal behavior distribution while being poorly supported jointly with the surrounding-agent behavior observed in the logged interaction. We refer to this degradation in interaction support as \emph{interaction distribution shift} (IDS), and introduce \emph{Interaction-Constrained Drive Policy} (ICDP), an offline reinforcement learning framework that explicitly controls interaction-level distribution shift. Starting from the joint data distribution over ego and surrounding-agent futures, we show that joint-support degradation decomposes exactly into an ego-support component and a residual interaction-support component. We recover the latter through contrastive density-ratio estimation, isolating interaction compatibility without explicit joint-density modeling, surrounding-agent prediction, or rollouts in reactive simulators or learned world models during policy optimization. Closed-loop evaluations on nuPlan, Interplan and real-world truck experiments show that ICDP suppresses high-value yet interaction-unsupported trajectory selections and improves performance in interaction-critical driving scenarios. Project webpage: this https URL
| Comments: | Corrected affiliation formatting and some typos |
| Subjects: | Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Robotics (cs.RO) |
| Cite as: | arXiv:2610.09763 [cs.LG] |
| (or arXiv:2610.09763v2 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.09763 arXiv-issued DOI via DataCite |
Submission history
From: Mahmoud Selim [view email]
[v1]
Wed, 7 Oct 2026 09:48:53 UTC (4,687 KB)
[v2]
Mon, 12 Oct 2026 19:56:25 UTC (4,687 KB)
来源：arXiv cs.AI · arxiv.org