分解多智能体交互，让自动驾驶仿真更真实。
DecompGAIL: Learning Realistic Traffic Behaviors with Decomposed Multi-Agent Generative Adversarial Imitation Learning
- 拆分驾驶行为真实性，分离自身与邻车影响
- 在WOMD基准上达到当前最优仿真效果
- 适合自动驾驶仿真与城市交通规划研究
真实交通仿真对自动驾驶系统和城市交通规划至关重要，但现有模仿学习方法难以建模真实交通行为。行为克隆存在协变量偏移问题，而生成对抗模仿学习（GAIL）在多智能体场景中极不稳定。我们发现不相关交互误导是主要原因：判别器因邻车不真实互动而惩罚本车合理行为。为此，提出分解式多智能体GAIL（DecompGAIL），将真实性显式分解为本车-地图与本车-邻车两部分，过滤掉邻车间及邻车-地图的误导性交互。进一步引入社会PPO目标，通过距离加权的邻近奖励增强本车奖励，促进整体行为真实。集成于轻量级SMART骨干网络，在WOMD Sim Agents 2025基准上取得当前最优性能。
原文摘要 · Abstract (English)
Realistic traffic simulation is critical for the development of autonomous driving systems and urban mobility planning, yet existing imitation learning approaches often fail to model realistic traffic behaviors. Behavior cloning suffers from covariate shift, while Generative Adversarial Imitation Learning (GAIL) is notoriously unstable in multi-agent settings. We identify a key source of this instability: irrelevant interaction misguidance, where a discriminator penalizes an ego vehicle's realistic behavior due to unrealistic interactions among its neighbors. To address this, we propose Decomposed Multi-agent GAIL (DecompGAIL), which explicitly decomposes realism into ego-map and ego-neighbor components, filtering out misleading neighbor: neighbor and neighbor: map interactions. We further introduce a social PPO objective that augments ego rewards with distance-weighted neighborhood rewards, encouraging overall realism across agents. Integrated into a lightweight SMART-based backbone, DecompGAIL achieves state-of-the-art performance on the WOMD Sim Agents 2025 benchmark.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。