Beyond Self-Play and Scale: A Behavior Benchmark for Generalization in Autonomous Driving

• URL: http://arxiv.org/abs/2605.10034v1
• Date: Mon, 11 May 2026 05:59:49 GMT
• Title: Beyond Self-Play and Scale: A Behavior Benchmark for Generalization in Autonomous Driving
• Abstract summary: Recent Autonomous Driving (AD) works have unlocked Reinforcement Learning (RL) at scale as a training strategy for driving policies.<n>Yet such policies remain disconnected from established benchmarks, leaving the performance of large-scale RL for driving on standardized evaluations unknown.<n>We present BehaviorBench -- a comprehensive test suite that closes this gap along three axes: Evaluation, Complexity, and Behavior Diversity.
• Score: 8.06426702612716
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent Autonomous Driving (AD) works such as GigaFlow and PufferDrive have unlocked Reinforcement Learning (RL) at scale as a training strategy for driving policies. Yet such policies remain disconnected from established benchmarks, leaving the performance of large-scale RL for driving on standardized evaluations unknown. We present BehaviorBench -- a comprehensive test suite that closes this gap along three axes: Evaluation, Complexity, and Behavior Diversity. In terms of Evaluation, we provide an interface connecting PufferDrive to nuPlan, which, for the first time, enables policies trained via RL at scale to be evaluated on an established planning benchmark for autonomous driving. Complementarily, we offer an evaluation framework that allows planners to be benchmarked directly inside the PufferDrive simulation, at a fraction of the time. Regarding Complexity, we observe that today's standardized benchmarks are so simple that near-perfect scores are achievable by straight lane following with collision checking. We extract a meaningful, interaction-rich split from the Waymo Open Motion Dataset (WOMD) on which strong performance is impossible without multi-agent reasoning. Lastly, we address Behavior Diversity. Existing benchmarks commonly evaluate planners against a single rule-based traffic model, the Intelligent Driver Model (IDM). We provide a diverse suite of interactive traffic agents to stress-test policies under heterogeneous behaviors, beyond just using IDM. Overall, our benchmarking analysis uncovers the following insight: despite learning interactive behaviors in an emergent manner, policies trained via pure self-play under standard reward functions overfit to their training opponents and fail to generalize to other traffic agent behaviors. Building on this observation, we propose a hybrid planner that combines a PPO policy with a rule-based planner.

Related papers

• ReactSim-Bench: Benchmarking Reactive Behavior World Model Simulation in Autonomous Driving [56.96697737229895]
  Reactive capability is a key property of data-driven behavior world model simulators for autonomous driving simulation systems.<n>We introduce ReactSim-Bench for evaluating the reactive capability of behavior world model simulation in autonomous driving.
  arXiv  Detail & Related papers  (2026-06-12T03:11:06Z)
• Model-Based Policy Adaptation for Closed-Loop End-to-End Autonomous Driving [54.46325690390831]
  We propose Model-based Policy Adaptation (MPA), a general framework that enhances the robustness and safety of pretrained E2E driving agents during deployment.<n>MPA first generates diverse counterfactual trajectories using a geometry-consistent simulation engine.<n>MPA trains a diffusion-based policy adapter to refine the base policy's predictions and a multi-step Q value model to evaluate long-term outcomes.
  arXiv  Detail & Related papers  (2025-11-26T17:01:41Z)
• nuPlan-R: A Closed-Loop Planning Benchmark for Autonomous Driving via Reactive Multi-Agent Simulation [2.585002881750625]
  We present nuPlan-R, a new reactive closed-loop planning benchmark.<n>Our benchmark replaces the rule-based IDM agents with noise-decoupled diffusion-based reactive agents.<n>We extend the benchmark with two additional metrics to enable a more comprehensive assessment of planning performance.
  arXiv  Detail & Related papers  (2025-11-13T15:23:30Z)
• 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)
• When Planners Meet Reality: How Learned, Reactive Traffic Agents Shift nuPlan Benchmarks [39.146761527401424]
  Rule-based traffic agents hide planner deficiencies and bias rankings.<n>We integrate the state-of-the-art learned traffic agent model SMART into nuPlan.<n>Our analysis shows that IDM-based simulation overestimates planning performance.
  arXiv  Detail & Related papers  (2025-10-16T13:34:12Z)
• Bench4Merge: A Comprehensive Benchmark for Merging in Realistic Dense Traffic with Micro-Interactive Vehicles [21.832221839624527]
  We propose a benchmark for assessing motion planning capabilities in merging scenarios.<n>Our approach involves other vehicles trained in large scale datasets with micro-behavioral characteristics.<n>We have obtained an evaluation of existing methods and identified common issues.
  arXiv  Detail & Related papers  (2024-10-21T11:35:33Z)
• Planning with Adaptive World Models for Autonomous Driving [50.4439896514353]
  We present nuPlan, a real-world motion planning benchmark that captures multi-agent interactions.<n>We learn to model such unique behaviors with BehaviorNet, a graph convolutional neural network (GCNN)<n>We also present AdaptiveDriver, a model-predictive control (MPC) based planner that unrolls different world models conditioned on BehaviorNet's predictions.
  arXiv  Detail & Related papers  (2024-06-15T18:53:45Z)
• 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)
• Learning to drive from a world on rails [78.28647825246472]
  We learn an interactive vision-based driving policy from pre-recorded driving logs via a model-based approach. A forward model of the world supervises a driving policy that predicts the outcome of any potential driving trajectory. Our method ranks first on the CARLA leaderboard, attaining a 25% higher driving score while using 40 times less data.
  arXiv  Detail & Related papers  (2021-05-03T05:55:30Z)
• Integrating Deep Reinforcement Learning with Model-based Path Planners for Automated Driving [0.0]
  We propose a hybrid approach for integrating a path planning pipe into a vision based DRL framework. In summary, the DRL agent is trained to follow the path planner's waypoints as close as possible. Experimental results show that the proposed method can plan its path and navigate between randomly chosen origin-destination points.
  arXiv  Detail & Related papers  (2020-02-02T17:10:19Z)

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.