mlsanityData to 7 Oct 2026

Inverse Reinforcement Learning Based Stochastic Driver Behavior Learning

arXiv 2107.06344 ↗First posted 1 Jul 2021cs.LG cs.SY eess.SYcited by 3

On the map: Offline RL and imitation learning from data → Imitation and offline RL for driving

Abstract (arXiv)

Drivers have unique and rich driving behaviors when operating vehicles in traffic. This paper presents a novel driver behavior learning approach that captures the uniqueness and richness of human driver behavior in realistic driving scenarios. A stochastic inverse reinforcement learning (SIRL) approach is proposed to learn a distribution of cost function, which represents the richness of the human driver behavior with a given set of driver-specific demonstrations. Evaluations are conducted on the realistic driving data collected from the 3D driver-in-the-loop driving simulation. The results show that the learned stochastic driver model is capable of expressing the richness of the human driving strategies under different realistic driving scenarios. Compared to the deterministic baseline driver behavior model, the results reveal that the proposed stochastic driver behavior model can better replicate the driver's unique and rich driving strategies in a variety of traffic conditions.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Placed in Imitation and offline RL for driving, one of 13 directions in Offline RL and imitation learning from data. Builds on 5 of its 23 references that are in the map. First posted on arXiv 1 Jul 2021.

Builds on

5 of 23 references.

Closest ancestors · 2

Same direction, newest first

  1. 2020Efficient Sampling-Based Maximum Entropy Inverse Reinforcement Learning with Application to Autonomous Driving22 Jun
  2. 2019Driving with Style: Inverse Reinforcement Learning in General-Purpose Planning for Automated Driving1 May

Other references · 3

  1. 2014Efficient Model Learning for Human-Robot Collaborative Taskscited by 35
  2. 2020Expressing Diverse Human Driving Behavior with Probabilistic Rewards and Online Inferencecited by 4
  3. 2021Personalized Adaptive Cruise Control and Impacts on Mixed Trafficcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 1; 2023: 0; 2024: 0; 2025: 1; 2026: 1.

3 papers.

  1. 2025HAD-Gen: Human-like and Diverse Driving Behavior Modeling for Controllable Scenario Generationcited by 3
  2. 2022Mathematical Models of Human Drivers Using Artificial Risk Fieldscited by 0
  3. 2026Game-Theoretic Inverse Reinforcement Learning for Modeling Competitive Human Driving: A Cut-in Prediction Studycited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2020Driving Behavior Modeling using Naturalistic Human Driving Data with Inverse Reinforcement Learning
  2. 2018Probabilistic Prediction of Interactive Driving Behavior via Hierarchical Inverse Reinforcement Learning
  3. 2022Conditional Predictive Behavior Planning with Inverse Reinforcement Learning for Human-like Autonomous Driving
  4. 2022Inverse Resource Rational Based Stochastic Driver Behavior Model ↗
  5. 2020Modeling Human Driving Behavior through Generative Adversarial Imitation Learning
  6. 2023Identifying Reaction-Aware Driving Styles of Stochastic Model Predictive Controlled Vehicles by Inverse Reinforcement Learning
  7. 2020Guided Policy Search Model-based Reinforcement Learning for Urban Autonomous Driving
  8. 2022Driving in Real Life with Inverse Reinforcement Learning