SPACeR: Self-Play Anchoring with Centralized Reference Models

• URL: http://arxiv.org/abs/2510.18060v1
• Date: Mon, 20 Oct 2025 19:53:02 GMT
• Title: SPACeR: Self-Play Anchoring with Centralized Reference Models
• Authors: Wei-Jer Chang, Akshay Rangesh, Kevin Joseph, Matthew Strong, Masayoshi Tomizuka, Yihan Hu, Wei Zhan,
• Abstract summary: 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.
• Score: 50.55045557371374
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Developing autonomous vehicles (AVs) requires not only safety and efficiency, but also realistic, human-like behaviors that are socially aware and predictable. Achieving this requires sim agent policies that are human-like, fast, and scalable in multi-agent settings. Recent progress in imitation learning with large diffusion-based or tokenized models has shown that behaviors can be captured directly from human driving data, producing realistic policies. However, these models are computationally expensive, slow during inference, and struggle to adapt in reactive, closed-loop scenarios. In contrast, self-play reinforcement learning (RL) scales efficiently and naturally captures multi-agent interactions, but it often relies on heuristics and reward shaping, and the resulting policies can diverge from human norms. We propose SPACeR, a framework that leverages a pretrained tokenized autoregressive motion model as a centralized reference policy to guide decentralized self-play. The reference model provides likelihood rewards and KL divergence, anchoring policies to the human driving distribution while preserving RL scalability. Evaluated on the Waymo Sim Agents Challenge, our method achieves competitive performance with imitation-learned policies while being up to 10x faster at inference and 50x smaller in parameter size than large generative models. In addition, we demonstrate in closed-loop ego planning evaluation tasks that our sim agents can effectively measure planner quality with fast and scalable traffic simulation, establishing a new paradigm for testing autonomous driving policies.

Related papers

• STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning [54.28691219536054]
  We introduce STARec, a slow-thinking augmented agent framework that endows recommender systems with autonomous deliberative reasoning capabilities.<n>We develop anchored reinforcement training - a two-stage paradigm combining structured knowledge distillation from advanced reasoning models with preference-aligned reward shaping.<n>Experiments on MovieLens 1M and Amazon CDs benchmarks demonstrate that STARec achieves substantial performance gains compared with state-of-the-art baselines.
  arXiv  Detail & Related papers  (2025-08-26T08:47:58Z)
• Rolling Ahead Diffusion for Traffic Scene Simulation [13.900806577888861]
  Realistic driving simulation requires that NPCs not only mimic natural driving behaviors but also react to the behavior of other simulated agents.<n>Recent developments in diffusion-based scenario generation focus on creating diverse and realistic traffic scenarios.<n>We present a rolling diffusion based traffic scene generation model which mixes the benefits of both methods.
  arXiv  Detail & Related papers  (2025-02-13T18:45:56Z)
• CtRL-Sim: Reactive and Controllable Driving Agents with Offline Reinforcement Learning [38.63187494867502]
  CtRL-Sim is a method that leverages return-conditioned offline reinforcement learning (RL) to efficiently generate reactive and controllable traffic agents. We show that CtRL-Sim can generate realistic safety-critical scenarios while providing fine-grained control over agent behaviours.
  arXiv  Detail & Related papers  (2024-03-29T02:10:19Z)
• SAFE-SIM: Safety-Critical Closed-Loop Traffic Simulation with Diffusion-Controllable Adversaries [94.84458417662407]
  We introduce SAFE-SIM, a controllable closed-loop safety-critical simulation framework. Our approach yields two distinct advantages: 1) generating realistic long-tail safety-critical scenarios that closely reflect real-world conditions, and 2) providing controllable adversarial behavior for more comprehensive and interactive evaluations. We validate our framework empirically using the nuScenes and nuPlan datasets across multiple planners, demonstrating improvements in both realism and controllability.
  arXiv  Detail & Related papers  (2023-12-31T04:14:43Z)
• Fully Decentralized Model-based Policy Optimization for Networked Systems [23.46407780093797]
  This work aims to improve data efficiency of multi-agent control by model-based learning. We consider networked systems where agents are cooperative and communicate only locally with their neighbors. In our method, each agent learns a dynamic model to predict future states and broadcast their predictions by communication, and then the policies are trained under the model rollouts.
  arXiv  Detail & Related papers  (2022-07-13T23:52:14Z)
• Your Autoregressive Generative Model Can be Better If You Treat It as an Energy-Based One [83.5162421521224]
  We propose a unique method termed E-ARM for training autoregressive generative models. E-ARM takes advantage of a well-designed energy-based learning objective. We show that E-ARM can be trained efficiently and is capable of alleviating the exposure bias problem.
  arXiv  Detail & Related papers  (2022-06-26T10:58:41Z)
• PerSim: Data-Efficient Offline Reinforcement Learning with Heterogeneous Agents via Personalized Simulators [19.026312915461553]
  We propose a model-based offline reinforcement learning (RL) approach called PerSim. We first learn a personalized simulator for each agent by collectively using the historical trajectories across all agents prior to learning a policy. This representation suggests a simple, regularized neural network architecture to effectively learn the transition dynamics per agent, even with scarce, offline data.
  arXiv  Detail & Related papers  (2021-02-13T17:16:41Z)
• 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)
• Learning from Simulation, Racing in Reality [126.56346065780895]
  We present a reinforcement learning-based solution to autonomously race on a miniature race car platform. We show that a policy that is trained purely in simulation can be successfully transferred to the real robotic setup.
  arXiv  Detail & Related papers  (2020-11-26T14:58:49Z)
• FormulaZero: Distributionally Robust Online Adaptation via Offline Population Synthesis [34.07399367947566]
  autonomous racing is a domain that penalizes safe but conservative policies. Current approaches either make simplifying assumptions about other agents or lack robust mechanisms for online adaptation. We develop a novel method for self-play based on replica-exchange Markov chain Monte Carlo.
  arXiv  Detail & Related papers  (2020-03-09T03:07:57Z)

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.