mlsanityData to 7 Oct 2026

Efficient and Generalized end-to-end Autonomous Driving System with Latent Deep Reinforcement Learning and Demonstrations

arXiv 2401.11792 ↗First posted 22 Jan 2024cs.RO cs.AI cs.LGcited by 7

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

Abstract (arXiv)

An intelligent driving system should dynamically formulate appropriate driving strategies based on the current environment and vehicle status while ensuring system security and reliability. However, methods based on reinforcement learning and imitation learning often suffer from high sample complexity, poor generalization, and low safety. To address these challenges, this paper introduces an efficient and generalized end-to-end autonomous driving system (EGADS) for complex and varied scenarios. The RL agent in our EGADS combines variational inference with normalizing flows, which are independent of distribution assumptions. This combination allows the agent to capture historical information relevant to driving in latent space effectively, thereby significantly reducing sample complexity. Additionally, we enhance safety by formulating robust safety constraints and improve generalization and performance by integrating RL with expert demonstrations. Experimental results demonstrate that, compared to existing methods, EGADS significantly reduces sample complexity, greatly improves safety performance, and exhibits strong generalization capabilities in complex urban scenarios. Particularly, we contributed an expert dataset collected through human expert steering wheel control, specifically using the G29 steering wheel.

Key facts. Cited by 7 papers in the map (data through 7 Oct 2026). Placed in Reinforcement learning for driving, one of 9 directions in End-to-end autonomous driving. Builds on 33 of its 52 references that are in the map. First posted on arXiv 22 Jan 2024.

Builds on

33 of 52 references.

Closest ancestors · 5

Same direction, newest first

  1. 2024HAIM-DRL: Enhanced Human-in-the-loop Reinforcement Learning for Safe and Efficient Autonomous Driving6 Jan
  2. 2023Safe Navigation: Training Autonomous Vehicles using Deep Reinforcement Learning in CARLA23 Oct
  3. 2023Identify, Estimate and Bound the Uncertainty of Reinforcement Learning for Autonomous Driving12 May
  4. 2022Augmenting Reinforcement Learning with Transformer-based Scene Representation Learning for Decision-making of Autonomous Driving24 Aug
  5. 2021Improved Deep Reinforcement Learning with Expert Demonstrations for Urban Autonomous Driving18 Feb

Other references · 28

  1. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,635
  2. 2015Continuous control with deep reinforcement learningcited by 3,279
  3. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  4. 2018Addressing Function Approximation Error in Actor-Critic Methodscited by 2,302
  5. 2015Variational Inference with Normalizing Flowscited by 2,161
  6. 2016Density estimation using Real NVPcited by 2,029
  7. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,777
  8. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
  9. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
  10. 2016End to End Learning for Self-Driving Carscited by 1,000
  11. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 685
  12. 2017End-to-end Driving via Conditional Imitation Learningcited by 479
16 more
  1. 2018ChauffeurNet: Learning to Drive by Imitating the Best and Synthesizing the Worstcited by 391
  2. 2018Learning to Drive in a Daycited by 266
  3. 2016A Survey of Motion Planning and Control Techniques for Self-driving Urban Vehiclescited by 251
  4. 2018Neural Autoregressive Flowscited by 207
  5. 2016Deep Variational Bayes Filters: Unsupervised Learning of State Space Models from Raw Datacited by 154
  6. 2020Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learningcited by 99
  7. 2019Model-free Deep Reinforcement Learning for Urban Autonomous Drivingcited by 96
  8. 2019Block Neural Autoregressive Flowcited by 62
  9. 2019Deep Imitation Learning for Autonomous Driving in Generic Urban Scenarios with Enhanced Safetycited by 48
  10. 2022Enhance Sample Efficiency and Robustness of End-to-end Urban Autonomous Driving via Semantic Masked World Modelcited by 44
  11. 2022Conditional Predictive Behavior Planning with Inverse Reinforcement Learning for Human-like Autonomous Drivingcited by 34
  12. 2023Large Language Model as a Policy Teacher for Training Reinforcement Learning Agentscited by 30
  13. 2022Flow-based Recurrent Belief State Learning for POMDPscited by 16
  14. 2022Spatial-Temporal-Aware Safe Multi-Agent Reinforcement Learning of Connected Autonomous Vehicles in Challenging Scenarioscited by 12
  15. 2023On Context Distribution Shift in Task Representation Learning for Offline Meta RLcited by 4
  16. 2023Partial End-to-end Reinforcement Learning for Robustness Against Modelling Error in Autonomous Racingcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 3.

7 papers.

  1. 2025One Subgoal at a Time: Zero-Shot Generalization to Arbitrary Linear Temporal Logic Requirements in Multi-Task Reinforcement Learningcited by 8
  2. 2026One Token Per Frame: Reconsidering Visual Bandwidth in World Models for VLA Policycited by 6
  3. 2024VLASCD: A Visual Language Action Model for Simultaneous Chatting and Decision Makingcited by 5
  4. 2025DriveMind: A Dual Visual Language Model-based Reinforcement Learning Framework for Autonomous Drivingcited by 3
  5. 2026Latent World Models for Automated Driving: A Unified Taxonomy, Evaluation Framework, and Open Challengescited by 3
  6. 2025A Practical Introduction to Deep Reinforcement Learningcited by 0
  7. 2026When Can You Poison Rewards? A Tight Characterization of Reward Poisoning in Linear MDPscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning
  2. 2024From Imitation to Exploration: End-to-end Autonomous Driving based on World Model
  3. 2023Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors
  4. 2021Towards Learning Generalizable Driving Policies from Restricted Latent Representations
  5. 2021A Survey of Deep RL and IL for Autonomous Driving Policy Learning
  6. 2025V-Max: A Reinforcement Learning Framework for Autonomous Driving
  7. 2019Safer End-to-End Autonomous Driving via Conditional Imitation Learning and Command Augmentation
  8. 2025A Comprehensive Review of Reinforcement Learning for Autonomous Driving in the CARLA Simulator