DecompGAIL: Learning Realistic Traffic Behaviors with Decomposed Multi-Agent Generative Adversarial Imitation Learning

• URL: http://arxiv.org/abs/2510.06913v1
• Date: Wed, 08 Oct 2025 11:46:39 GMT
• Title: DecompGAIL: Learning Realistic Traffic Behaviors with Decomposed Multi-Agent Generative Adversarial Imitation Learning
• Abstract summary: Existing imitation learning approaches often fail to model realistic traffic behaviors.<n>We propose DecompGAIL, which explicitly decomposes realism into ego-map and ego-neighbor components.<n>DecompGAIL achieves state-of-the-art performance on the WOMD Sim Agents 2025 benchmark.
• Score: 59.63038625580992
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• World Models as Adversaries: Multi-Agent Self-Play Fine-Tuning for Robust Motion Planning [60.88859946006306]
  Adversa World Modeling is a theoretically grounded multi-agent self-play fine-tuning framework.<n>In inner minimization, the planner's predictive world model is converted into a role-conditioned adversary that learns sparse, scene-adaptive attack coalitions.<n> Experiments on the nuPlan and InterPlan benchmarks demonstrate that our method generates transferable adversarial interactions.
  arXiv  Detail & Related papers  (2026-07-12T07:44:16Z)
• MAPLE: Latent Multi-Agent Play for End-to-End Autonomous Driving [62.43744546817599]
  Vision-language--action (VLA) models are effective as end-to-end motion planners, but can be brittle when evaluated in closed-loop settings.<n>We propose MAPLE, a novel framework for reactive, multi-agent rollout of a dynamic driving scenario in the latent space of the VLA model.<n> MAPLE achieves state-of-the-art driving performance on Bench2Drive and demonstrates scalable, closed-loop multi-agent play for robust E2E autonomous driving systems.
  arXiv  Detail & Related papers  (2026-05-13T23:35:14Z)
• Beyond Self-Play: Hierarchical Reasoning for Continuous Motion in Closed-Loop Traffic Simulation [8.157621070273736]
  We propose a hierarchical architecture that goes beyond self-play by combining high-level multi-agent interaction reasoning with low-level continuous trajectory realization.<n>Experiments on a SUMO-based urban network demonstrate that the proposed framework achieves smoothness superior control and safety compared to self-play and passive imitation baselines.
  arXiv  Detail & Related papers  (2026-05-09T20:31:34Z)
• Position: AI Agents Are Not (Yet) a Panacea for Social Simulation [62.891898598784415]
  Recent advances in large language models (LLMs) have spurred growing interest in using LLM-integrated agents for social simulation.<n>This position paper argues that LLM-based agents are not (yet) a panacea for social simulation.
  arXiv  Detail & Related papers  (2026-02-19T06:35:07Z)
• ForSim: Stepwise Forward Simulation for Traffic Policy Fine-Tuning [13.668397738433852]
  ForSim is a stepwise closed-loop forward simulation paradigm.<n>It preserves multimodal behavioral diversity while ensuring intra-modality consistency.<n>ForSim operates in conjunction with group-relative optimization to fine-tune traffic policy.
  arXiv  Detail & Related papers  (2026-02-02T10:20:11Z)
• Optimization-Guided Diffusion for Interactive Scene Generation [52.23368750264419]
  We present OMEGA, an optimization-guided, training-free framework that enforces structural consistency and interaction awareness during diffusion-based sampling.<n>We show that OMEGA improves generation realism, consistency, and controllability, increasing the ratio of physically and behaviorally valid scenes.<n>Our approach can also generate $5times$ more near-collision frames with a time-to-collision under three seconds.
  arXiv  Detail & Related papers  (2025-12-08T15:56:18Z)
• SocialDriveGen: Generating Diverse Traffic Scenarios with Controllable Social Interactions [28.77173801411955]
  SocialDriveGen is a hierarchical framework that integrates semantic reasoning and social preference modeling with generative trajectory synthesis.<n>By modeling egoism and altruism as complementary social dimensions, our framework enables controllable diversity in driver personalities and interaction styles.<n>Experiments on the Argoverse 2 dataset show that SocialDriveGen generates diverse, high-fidelity traffic scenarios spanning cooperative to adversarial behaviors.
  arXiv  Detail & Related papers  (2025-12-01T07:18:20Z)
• SPACeR: Self-Play Anchoring with Centralized Reference Models [50.55045557371374]
  Sim agent policies are realistic, human-like, fast, and scalable in multi-agent settings.<n>Recent progress in imitation learning with large diffusion-based or tokenized models has shown that behaviors can be captured directly from human driving data.<n>We propose SPACeR, a framework that leverages a pretrained tokenized autoregressive motion model as a central reference policy.
  arXiv  Detail & Related papers  (2025-10-20T19:53:02Z)
• Sim-to-Real Causal Transfer: A Metric Learning Approach to Causally-Aware Interaction Representations [58.96953392466609]
  We take an in-depth look at the causal awareness of modern representations of agent interactions.<n>We show that recent representations are already partially resilient to perturbations of non-causal agents.<n>We introduce a metric learning approach that regularizes latent representations with causal annotations.
  arXiv  Detail & Related papers  (2023-12-07T18:57:03Z)
• Interactive Autonomous Navigation with Internal State Inference and Interactivity Estimation [58.21683603243387]
  We propose three auxiliary tasks with relational-temporal reasoning and integrate them into the standard Deep Learning framework. These auxiliary tasks provide additional supervision signals to infer the behavior patterns other interactive agents. Our approach achieves robust and state-of-the-art performance in terms of standard evaluation metrics.
  arXiv  Detail & Related papers  (2023-11-27T18:57:42Z)
• PPAD: Iterative Interactions of Prediction and Planning for End-to-end Autonomous Driving [57.89801036693292]
  PPAD (Iterative Interaction of Prediction and Planning Autonomous Driving) considers the timestep-wise interaction to better integrate prediction and planning. We design ego-to-agent, ego-to-map, and ego-to-BEV interaction mechanisms with hierarchical dynamic key objects attention to better model the interactions.
  arXiv  Detail & Related papers  (2023-11-14T11:53:24Z)
• Symphony: Learning Realistic and Diverse Agents for Autonomous Driving Simulation [45.09881984441893]
  We propose Symphony, which greatly improves realism by combining conventional policies with a parallel beam search. Symphony addresses this issue with a hierarchical approach, factoring agent behaviour into goal generation and goal conditioning. Experiments confirm that Symphony agents learn more realistic and diverse behaviour than several baselines.
  arXiv  Detail & Related papers  (2022-05-06T13:21:40Z)
• TrafficSim: Learning to Simulate Realistic Multi-Agent Behaviors [74.67698916175614]
  We propose TrafficSim, a multi-agent behavior model for realistic traffic simulation. In particular, we leverage an implicit latent variable model to parameterize a joint actor policy. We show TrafficSim generates significantly more realistic and diverse traffic scenarios as compared to a diverse set of baselines.
  arXiv  Detail & Related papers  (2021-01-17T00:29:30Z)
• Modeling Human Driving Behavior through Generative Adversarial Imitation Learning [7.387855463533219]
  This article describes the use of Generative Adversarial Imitation Learning (GAIL) for learning-based driver modeling. Because driver modeling is inherently a multi-agent problem, this paper describes a parameter-sharing extension of GAIL called PS-GAIL to tackle multi-agent driver modeling. This paper describes Reward Augmented Imitation Learning (RAIL), which modifies the reward signal to provide domain-specific knowledge to the agent.
  arXiv  Detail & Related papers  (2020-06-10T05:47:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.