Tactical Decision-Making in Autonomous Driving by Reinforcement Learning with Uncertainty Estimation
Not on the map. Why?
Abstract (arXiv)
Reinforcement learning (RL) can be used to create a tactical decision-making agent for autonomous driving. However, previous approaches only output decisions and do not provide information about the agent's confidence in the recommended actions. This paper investigates how a Bayesian RL technique, based on an ensemble of neural networks with additional randomized prior functions (RPF), can be used to estimate the uncertainty of decisions in autonomous driving. A method for classifying whether or not an action should be considered safe is also introduced. The performance of the ensemble RPF method is evaluated by training an agent on a highway driving scenario. It is shown that the trained agent can estimate the uncertainty of its decisions and indicate an unacceptable level when the agent faces a situation that is far from the training distribution. Furthermore, within the training distribution, the ensemble RPF agent outperforms a standard Deep Q-Network agent. In this study, the estimated uncertainty is used to choose safe actions in unknown situations. However, the uncertainty information could also be used to identify situations that should be added to the training process.
Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). First posted on arXiv 22 Apr 2020.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 3; 2022: 3; 2023: 2; 2024: 2; 2025: 1; 2026: 3.
14 papers.
Sort:
By area:
- 2021Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulationcited by 85
- 2021Transformer Uncertainty Estimation with Hierarchical Stochastic Attentioncited by 21
- 2021Ensemble Quantile Networks: Uncertainty-Aware Reinforcement Learning with Applications in Autonomous Drivingcited by 17
- 2025Hybrid Action Based Reinforcement Learning for Multi-Objective Compatible Autonomous Drivingcited by 8
- 2023Identify, Estimate and Bound the Uncertainty of Reinforcement Learning for Autonomous Drivingcited by 6
- 2024Contextualized Hybrid Ensemble Q-learning: Learning Fast with Control Priorscited by 5
- 2023Failure Detection for Motion Prediction of Autonomous Driving: An Uncertainty Perspectivecited by 4
- 2024Tactical Decision Making for Autonomous Trucks by Deep Reinforcement Learning with Total Cost of Operation Based Rewardcited by 3
- 2026Pedestrian-Aware LLM-Driven Behavioral Planning for Autonomous Vehiclescited by 1
- 2022Automatically Learning Fallback Strategies with Model-Free Reinforcement Learning in Safety-Critical Driving Scenarioscited by 0
- 2022Safer Autonomous Driving in a Stochastic, Partially-Observable Environment by Hierarchical Contingency Planningcited by 0
- 2022MSVIPER: Improved Policy Distillation for Reinforcement-Learning-Based Robot Navigationcited by 0
- 2026Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty18 May 2026
- 2026Pedestrian-Aware LLM-Driven Behavioral Planning for Autonomous Vehicles16 May 2026
- 2026Preference-Conditioned Multi-Objective Reinforcement Learning for Tactical Decision Making in Heavy-Duty Vehicles26 Jan 2026
- 2025Hybrid Action Based Reinforcement Learning for Multi-Objective Compatible Autonomous Driving14 Jan 2025
- 2024Contextualized Hybrid Ensemble Q-learning: Learning Fast with Control Priors28 Jun 2024
- 2024Tactical Decision Making for Autonomous Trucks by Deep Reinforcement Learning with Total Cost of Operation Based Reward11 Mar 2024
- 2023Identify, Estimate and Bound the Uncertainty of Reinforcement Learning for Autonomous Driving12 May 2023
- 2023Failure Detection for Motion Prediction of Autonomous Driving: An Uncertainty Perspective11 Jan 2023
- 2022MSVIPER: Improved Policy Distillation for Reinforcement-Learning-Based Robot Navigation19 Sep 2022
- 2022Safer Autonomous Driving in a Stochastic, Partially-Observable Environment by Hierarchical Contingency Planning13 Apr 2022
- 2022Automatically Learning Fallback Strategies with Model-Free Reinforcement Learning in Safety-Critical Driving Scenarios11 Apr 2022
- 2021Transformer Uncertainty Estimation with Hierarchical Stochastic Attention27 Dec 2021
- 2021Ensemble Quantile Networks: Uncertainty-Aware Reinforcement Learning with Applications in Autonomous Drivingcited by 17
- 2025Hybrid Action Based Reinforcement Learning for Multi-Objective Compatible Autonomous Drivingcited by 8
- 2023Identify, Estimate and Bound the Uncertainty of Reinforcement Learning for Autonomous Drivingcited by 6
- 2026Pedestrian-Aware LLM-Driven Behavioral Planning for Autonomous Vehiclescited by 1
- 2022Automatically Learning Fallback Strategies with Model-Free Reinforcement Learning in Safety-Critical Driving Scenarioscited by 0
- 2022Safer Autonomous Driving in a Stochastic, Partially-Observable Environment by Hierarchical Contingency Planningcited by 0
- 2026Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertaintycited by 0
- 2026Multi-Agent Reinforcement Learning for Safe Autonomous Driving Under Pedestrian Behavioral Uncertainty18 May 2026
- 2026Pedestrian-Aware LLM-Driven Behavioral Planning for Autonomous Vehicles16 May 2026
- 2025Hybrid Action Based Reinforcement Learning for Multi-Objective Compatible Autonomous Driving14 Jan 2025
- 2023Identify, Estimate and Bound the Uncertainty of Reinforcement Learning for Autonomous Driving12 May 2023
- 2022Safer Autonomous Driving in a Stochastic, Partially-Observable Environment by Hierarchical Contingency Planning13 Apr 2022
- 2022Automatically Learning Fallback Strategies with Model-Free Reinforcement Learning in Safety-Critical Driving Scenarios11 Apr 2022
- 2021Ensemble Quantile Networks: Uncertainty-Aware Reinforcement Learning with Applications in Autonomous Driving21 May 2021
- 2024Contextualized Hybrid Ensemble Q-learning: Learning Fast with Control Priorscited by 5
- 2024Tactical Decision Making for Autonomous Trucks by Deep Reinforcement Learning with Total Cost of Operation Based Rewardcited by 3
- 2026Preference-Conditioned Multi-Objective Reinforcement Learning for Tactical Decision Making in Heavy-Duty Vehiclescited by 0
- 2026Preference-Conditioned Multi-Objective Reinforcement Learning for Tactical Decision Making in Heavy-Duty Vehicles26 Jan 2026
- 2024Contextualized Hybrid Ensemble Q-learning: Learning Fast with Control Priors28 Jun 2024
- 2024Tactical Decision Making for Autonomous Trucks by Deep Reinforcement Learning with Total Cost of Operation Based Reward11 Mar 2024
- 2021Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulationcited by 85
- 2021Transformer Uncertainty Estimation with Hierarchical Stochastic Attentioncited by 21
- 2023Failure Detection for Motion Prediction of Autonomous Driving: An Uncertainty Perspectivecited by 4
- 2022MSVIPER: Improved Policy Distillation for Reinforcement-Learning-Based Robot Navigationcited by 0
- 2023Failure Detection for Motion Prediction of Autonomous Driving: An Uncertainty Perspective11 Jan 2023
- 2022MSVIPER: Improved Policy Distillation for Reinforcement-Learning-Based Robot Navigation19 Sep 2022
- 2021Transformer Uncertainty Estimation with Hierarchical Stochastic Attention27 Dec 2021
- 2021Q-attention: Enabling Efficient Learning for Vision-based Robotic Manipulation31 May 2021