mlsanityData to 7 Oct 2026

OIL: Observational Imitation Learning

arXiv 1803.01129 ↗First posted 3 Mar 2018cs.CV cs.LG cs.ROcited by 11

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

Abstract (arXiv)

Recent work has explored the problem of autonomous navigation by imitating a teacher and learning an end-to-end policy, which directly predicts controls from raw images. However, these approaches tend to be sensitive to mistakes by the teacher and do not scale well to other environments or vehicles. To this end, we propose Observational Imitation Learning (OIL), a novel imitation learning variant that supports online training and automatic selection of optimal behavior by observing multiple imperfect teachers. We apply our proposed methodology to the challenging problems of autonomous driving and UAV racing. For both tasks, we utilize the Sim4CV simulator that enables the generation of large amounts of synthetic training data and also allows for online learning and evaluation. We train a perception network to predict waypoints from raw image data and use OIL to train another network to predict controls from these waypoints. Extensive experiments demonstrate that our trained network outperforms its teachers, conventional imitation learning (IL) and reinforcement learning (RL) baselines and even humans in simulation. The project website is available at https://sites.google.com/kaust.edu.sa/oil/ and a video at https://youtu.be/_rhq8a0qgeg

Key facts. Cited by 11 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 26 of its 49 references that are in the map. First posted on arXiv 3 Mar 2018.

Builds on

26 of 49 references.

References · 26

  1. 2015Continuous control with deep reinforcement learningcited by 3,279
  2. 2015Trust Region Policy Optimizationcited by 2,503
  3. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  4. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,218
  5. 2016Generative Adversarial Imitation Learningcited by 1,576
  6. 2016End to End Learning for Self-Driving Carscited by 1,000
  7. 2016Playing for Data: Ground Truth from Computer Gamescited by 816
  8. 2017Learning Complex Dexterous Manipulation with Deep Reinforcement Learning and Demonstrationscited by 685
  9. 2017AirSim: High-Fidelity Visual and Physical Simulation for Autonomous Vehiclescited by 517
  10. 2016Virtual Worlds as Proxy for Multi-Object Tracking Analysiscited by 340
  11. 2015DeepDriving: Learning Affordance for Direct Perception in Autonomous Drivingcited by 229
  12. 2017Deep Reinforcement Learning framework for Autonomous Drivingcited by 224
14 more
  1. 2016End-to-end Learning of Driving Models from Large-scale Video Datasetscited by 147
  2. 2018Reinforcement and Imitation Learning for Diverse Visuomotor Skillscited by 124
  3. 2014Reinforcement and Imitation Learning via Interactive No-Regret Learningcited by 116
  4. 2017Deeply AggreVaTeD: Differentiable Imitation Learning for Sequential Predictioncited by 93
  5. 2016Query-Efficient Imitation Learning for End-to-End Autonomous Drivingcited by 83
  6. 2018Reinforcement Learning from Imperfect Demonstrationscited by 74
  7. 2016Learning Physical Intuition of Block Towers by Examplecited by 66
  8. 2015Learning to Search Better Than Your Teachercited by 50
  9. 2016Learning to Act by Predicting the Futurecited by 36
  10. 2017Sim4CV: A Photo-Realistic Simulator for Computer Vision Applicationscited by 31
  11. 2016End-to-End Deep Reinforcement Learning for Lane Keeping Assistcited by 27
  12. 2017Navigating Occluded Intersections with Autonomous Vehicles using Deep Reinforcement Learningcited by 21
  13. 2018A Real-Time Game Theoretic Planner for Autonomous Two-Player Drone Racingcited by 21
  14. 2017Toward Low-Flying Autonomous MAV Trail Navigation using Deep Neural Networks for Environmental Awarenesscited by 17

Built on by

Cited by year

Citing papers per year: 2020: 1; 2021: 1; 2022: 2; 2023: 4; 2024: 1; 2025: 2.

11 papers.

  1. 2023Motion Planning for Autonomous Driving: The State of the Art and Future Perspectivescited by 112
  2. 2023SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real Worldcited by 47
  3. 2021Learning by Watchingcited by 22
  4. 2023Coaching a Teachable Studentcited by 17
  5. 2022SelfD: Self-Learning Large-Scale Driving Policies From the Webcited by 16
  6. 2023Blending Imitation and Reinforcement Learning for Robust Policy Improvementcited by 16
  7. 2022Visual Attention Prediction Improves Performance of Autonomous Drone Racing Agentscited by 6
  8. 2020Active Imitation Learning from Multiple Non-Deterministic Teachers: Formulation, Challenges, and Algorithmscited by 4
  9. 2024Oracle-Efficient Reinforcement Learning for Max Value Ensemblescited by 1
  10. 2025A Review of Learning-Based Motion Planning: Toward a Data-Driven Optimal Control Approachcited by 1
  11. 2025Domain-Invariant Per-Frame Feature Extraction for Cross-Domain Imitation Learning with Visual Observationscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2019Improved Reinforcement Learning through Imitation Learning Pretraining Towards Image-based Autonomous Driving
  2. 2022Robust Learning from Observation with Model Misspecification
  3. 2023A Survey of Imitation Learning: Algorithms, Recent Developments, and Challenges
  4. 2021VOILA: Visual-Observation-Only Imitation Learning for Autonomous Navigation
  5. 2025Learning from Observation: A Survey of Recent Advances
  6. 2021Keyframe-Focused Visual Imitation Learning
  7. 2020Learning to Drive (L2D) as a Low-Cost Benchmark for Real-World Reinforcement Learning
  8. 2026Towards Generalisable Imitation Learning Through Conditioned Transition Estimation and Online Behaviour Alignment