mlsanityData to 14 Oct 2026

Interactive Double Deep Q-network: Integrating Human Interventions and Evaluative Predictions in Reinforcement Learning of Autonomous Driving

arXiv 2505.01440 ↗First posted 28 Apr 2025cs.LG cs.AI cs.ROcited by 0

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

also in 2 more
Abstract (arXiv)

Integrating human expertise with machine learning is crucial for applications demanding high accuracy and safety, such as autonomous driving. This study introduces Interactive Double Deep Q-network (iDDQN), a Human-in-the-Loop (HITL) approach that enhances Reinforcement Learning (RL) by merging human insights directly into the RL training process, improving model performance. Our proposed iDDQN method modifies the Q-value update equation to integrate human and agent actions, establishing a collaborative approach for policy development. Additionally, we present an offline evaluative framework that simulates the agent's trajectory as if no human intervention had occurred, to assess the effectiveness of human interventions. Empirical results in simulated autonomous driving scenarios demonstrate that iDDQN outperforms established approaches, including Behavioral Cloning (BC), HG-DAgger, Deep Q-Learning from Demonstrations (DQfD), and vanilla DRL in leveraging human expertise for improving performance and adaptability.

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 13 of its 27 references that are in the map. First posted on arXiv 28 Apr 2025.

Builds on

13 of 27 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors8 May
  2. 2022Efficient Learning of Safe Driving Policy via Human-AI Copilot Optimization17 Feb
  3. 2021Human-in-the-Loop Deep Reinforcement Learning with Application to Autonomous Driving15 Apr

Other references · 10

  1. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  2. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,417
  3. 2015Deep Reinforcement Learning with Double Q-learningcited by 1,745
  4. 2015Prioritized Experience Replaycited by 1,099
  5. 2015Dueling Network Architectures for Deep Reinforcement Learningcited by 785
  6. 2017AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehiclescited by 523
  7. 2018Behavioral Cloning from Observationcited by 492
  8. 2018HG-DAgger: Interactive Imitation Learning with Human Expertscited by 266
  9. 2022Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deploymentcited by 108
  10. 2018DQN-TAMER: Human-in-the-Loop Reinforcement Learning with Intractable Feedbackcited by 41

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024HAIM-DRL: Enhanced Human-in-the-loop Reinforcement Learning for Safe and Efficient Autonomous Driving
  2. 2024Self-Driving Car Racing: Application of Deep Reinforcement Learning
  3. 2021DQ-GAT: Towards Safe and Efficient Autonomous Driving with Deep Q-Learning and Graph Attention Networks
  4. 2021Efficient Deep Reinforcement Learning with Imitative Expert Priors for Autonomous Driving
  5. 2021Modified DDPG car-following model with a real-world human driving experience with CARLA simulator
  6. 2024Mix Q-learning for Lane Changing: A Collaborative Decision-Making Method in Multi-Agent Deep Reinforcement Learning
  7. 2021An Independent Study of Reinforcement Learning and Autonomous Driving
  8. 2024Enhancing High-Speed Cruising Performance of Autonomous Vehicles through Integrated Deep Reinforcement Learning Framework