mlsanityData to 7 Oct 2026

Learning To Simulate

arXiv 1810.02513 ↗First posted 5 Oct 2018cs.LG cs.CV stat.MLcited by 43

Not on the map. Why?

Abstract (arXiv)

Simulation is a useful tool in situations where training data for machine learning models is costly to annotate or even hard to acquire. In this work, we propose a reinforcement learning-based method for automatically adjusting the parameters of any (non-differentiable) simulator, thereby controlling the distribution of synthesized data in order to maximize the accuracy of a model trained on that data. In contrast to prior art that hand-crafts these simulation parameters or adjusts only parts of the available parameters, our approach fully controls the simulator with the actual underlying goal of maximizing accuracy, rather than mimicking the real data distribution or randomly generating a large volume of data. We find that our approach (i) quickly converges to the optimal simulation parameters in controlled experiments and (ii) can indeed discover good sets of parameters for an image rendering simulator in actual computer vision applications.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). First posted on arXiv 5 Oct 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 12; 2023: 12; 2024: 4; 2025: 2; 2026: 1.

43 papers.

Sort:

By area:

  1. 2021DriveGAN: Towards a Controllable High-Quality Neural Simulationcited by 125
  2. 2022Adversarial Style Augmentation for Domain Generalized Urban-Scene Segmentationcited by 69
  3. 2021Robot Learning from Randomized Simulations: A Reviewcited by 56
  4. 2022Neural-Sim: Learning to Generate Training Data with NeRFcited by 27
  5. 2021Task2Sim : Towards Effective Pre-training and Transfer from Synthetic Datacited by 26
  6. 2023Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlationcited by 25
  7. 2024DataEnvGym: Data Generation Agents in Teacher Environments with Student Feedbackcited by 23
  8. 2021Less is More: Learning from Synthetic Data with Fine-grained Attributes for Person Re-Identificationcited by 19
  9. 2023AdaptSim: Task-Driven Simulation Adaptation for Sim-to-Real Transfercited by 17
  10. 2023Conditional Generators for Limit Order Book Environments: Explainability, Challenges, and Robustnesscited by 14
  11. 2021Simulated Adversarial Testing of Face Recognition Modelscited by 10
  12. 2021DR2L: Surfacing Corner Cases to Robustify Autonomous Driving via Domain Randomization Reinforcement Learningcited by 10
31 more
  1. 2021Learning an Explicit Hyperparameter Prediction Function Conditioned on Taskscited by 9
  2. 2022Attribute Descent: Simulating Object-Centric Datasets on the Content Level and Beyondcited by 9
  3. 2022Improving Adversarial Robustness by Contrastive Guided Diffusion Processcited by 8
  4. 2022Finding Differences Between Transformers and ConvNets Using Counterfactual Simulation Testingcited by 6
  5. 2021How to Synthesize a Large-Scale and Trainable Micro-Expression Dataset?cited by 4
  6. 2022Learning Pair Potentials using Differentiable Simulationscited by 4
  7. 2023Training with Product Digital Twins for AutoRetail Checkoutcited by 4
  8. 2023Alice Benchmarks: Connecting Real World Re-Identification with the Syntheticcited by 4
  9. 2021Photoacoustic image synthesis with generative adversarial networkscited by 3
  10. 2021High-Quality Diversification for Task-Oriented Dialogue Systemscited by 3
  11. 2022Human Body Measurement Estimation with Adversarial Augmentationcited by 3
  12. 2023Transformer-Based Neural Surrogate for Link-Level Path Loss Prediction from Variable-Sized Mapscited by 3
  13. 2023Multi-fidelity Constrained Optimization for Stochastic Black Box Simulatorscited by 3
  14. 2022TRoVE: Transforming Road Scene Datasets into Photorealistic Virtual Environmentscited by 2
  15. 2025MetaSTNet: Multimodal Meta-learning for Cellular Traffic Conformal Predictioncited by 2
  16. 2021Calibrating Over-Parametrized Simulation Models: A Framework via Eligibility Setcited by 1
  17. 2022Reinforcement Teachingcited by 1
  18. 2022Goldilocks-curriculum Domain Randomization and Fractal Perlin Noise with Application to Sim2Real Pneumonia Lesion Detectioncited by 1
  19. 2022Meta-simulation for the Automated Design of Synthetic Overhead Imagerycited by 1
  20. 2022Scalable Modular Synthetic Data Generation for Advancing Aerial Autonomycited by 1
  21. 2023INTAGS: Interactive Agent-Guided Simulationcited by 1
  22. 2023Learning Hybrid Dynamics Models With Simulator-Informed Latent Statescited by 1
  23. 2023AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registrationcited by 1
  24. 2023It HAS to be Subjective: Human Annotator Simulation via Zero-shot Density Estimationcited by 1
  25. 2024Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methodscited by 1
  26. 2021Man versus Machine: AutoML and Human Experts' Role in Phishing Detectioncited by 0
  27. 2023From concrete mixture to structural design -- a holistic optimization procedure in the presence of uncertaintiescited by 0
  28. 2024Simulating, Fast and Slow: Learning Policies for Black-Box Optimizationcited by 0
  29. 2024Learning Instance-Specific Parameters of Black-Box Models Using Differentiable Surrogatescited by 0
  30. 2025Evaluation of adaptive sampling methods in scenario generation for virtual safety impact assessment of pre-crash safety systemscited by 0
  31. 2026Can Synthetic Data Overcome the Generalization Limits of AI-Based Flower and Pod Detection Across Cowpea Breeding Genotypes and Environments?cited by 0