mlsanityData to 14 Oct 2026

Game-Theoretic Risk-Shaped Reinforcement Learning for Safe Autonomous Driving

arXiv 2510.10960 ↗First posted 13 Oct 2025cs.ROcited by 0

On the map: End-to-end autonomous driving → Reinforcement learning for driving

also in 1 more
Abstract (arXiv)

Ensuring safety in autonomous driving (AD) remains a significant challenge, especially in highly dynamic and complex traffic environments where diverse agents interact and unexpected hazards frequently emerge. Traditional reinforcement learning (RL) methods often struggle to balance safety, efficiency, and adaptability, as they primarily focus on reward maximization without explicitly modeling risk or safety constraints. To address these limitations, this study proposes a novel game-theoretic risk-shaped RL (GTR2L) framework for safe AD. GTR2L incorporates a multi-level game-theoretic world model that jointly predicts the interactive behaviors of surrounding vehicles and their associated risks, along with an adaptive rollout horizon that adjusts dynamically based on predictive uncertainty. Furthermore, an uncertainty-aware barrier mechanism enables flexible modulation of safety boundaries. A dedicated risk modeling approach is also proposed, explicitly capturing both epistemic and aleatoric uncertainty to guide constrained policy optimization and enhance decision-making in complex environments. Extensive evaluations across diverse and safety-critical traffic scenarios show that GTR2L significantly outperforms state-of-the-art baselines, including human drivers, in terms of success rate, collision and violation reduction, and driving efficiency. The code is available at https://github.com/DanielHu197/GTR2L.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Reinforcement learning for driving, one of 9 directions in End-to-end autonomous driving. Builds on 24 of its 44 references that are in the map. First posted on arXiv 13 Oct 2025.

Builds on

24 of 44 references.

Closest ancestors · 2

Same direction, newest first

  1. 2021Minimizing Safety Interference for Safe and Comfortable Automated Driving with Distributional Reinforcement Learning15 Jul
  2. 2021Ensemble Quantile Networks: Uncertainty-Aware Reinforcement Learning with Applications in Autonomous Driving21 May

Other references · 22

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  2. 2017Constrained Policy Optimizationcited by 983
  3. 2018Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Modelscited by 774
  4. 2019When to Trust Your Model: Model-Based Policy Optimizationcited by 773
  5. 2023End-to-end Autonomous Driving: Challenges and Frontierscited by 490
  6. 2018Reward Constrained Policy Optimizationcited by 417
  7. 2020Learning to Walk in the Real World with Minimal Human Effortcited by 111
  8. 2022Safe Reinforcement Learning by Imagining the Near Futurecited by 67
  9. 2021Safe Reinforcement Learning Using Robust Control Barrier Functionscited by 59
  10. 2022Reachability Constrained Reinforcement Learningcited by 59
  11. 2022Constrained Policy Optimization via Bayesian World Modelscited by 57
  12. 2020Enforcing robust control guarantees within neural network policiescited by 40
10 more
  1. 2020Verifiably Safe Exploration for End-to-End Reinforcement Learningcited by 34
  2. 2022Model-based Safe Deep Reinforcement Learning via a Constrained Proximal Policy Optimization Algorithmcited by 29
  3. 2024Language-Driven Policy Distillation for Cooperative Driving in Multi-Agent Reinforcement Learningcited by 14
  4. 2021Safe Exploration in Model-based Reinforcement Learning using Control Barrier Functionscited by 11
  5. 2023Safe Reinforcement Learning with Dual Robustnesscited by 10
  6. 2022Autonomous Highway Merging in Mixed Traffic Using Reinforcement Learning and Motion Predictive Safety Controllercited by 7
  7. 2024Risk-Aware Vehicle Trajectory Prediction Under Safety-Critical Scenarioscited by 7
  8. 2024Traffic expertise meets residual RL: Knowledge-informed model-based residual reinforcement learning for CAV trajectory controlcited by 7
  9. 2024Pre-trained Transformer-Enabled Strategies with Human-Guided Fine-Tuning for End-to-end Navigation of Autonomous Vehiclescited by 6
  10. 2022GIN: Graph-based Interaction-aware Constraint Policy Optimization for Autonomous Drivingcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Balancing Progress and Safety: A Novel Risk-Aware Objective for RL in Autonomous Driving
  2. 2025Uncertainty-Aware Safety-Critical Decision and Control for Autonomous Vehicles at Unsignalized Intersections
  3. 2021Risk-Constrained Interactive Safety under Behavior Uncertainty for Autonomous Driving
  4. 2025Learning Safe Autonomous Driving Policies Using Predictive Safety Representations
  5. 2023Risk-Aware Reward Shaping of Reinforcement Learning Agents for Autonomous Driving
  6. 2022SafeRL-Kit: Evaluating Efficient Reinforcement Learning Methods for Safe Autonomous Driving
  7. 2025Dynamic Residual Safe Reinforcement Learning for Multi-Agent Safety-Critical Scenarios Decision-Making
  8. 2026A Risk-Sensitive and Uncertainty-Aware Decision-Making and Control Framework for Safe and Robust Autonomous Driving