# Keep it Simple: Data-efficient Learning for Controlling Complex Systems with Simple Models

arXiv: https://arxiv.org/abs/2102.02493 · HTML: https://mlsanity.com/paper/2102.02493/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 35 references that are in the map.
- First posted on arXiv 4 Feb 2021.

## Builds on (most cited first, 22 of 22)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles](https://mlsanity.com/paper/1612.01474/) (2016)
- [Dream to Control: Learning Behaviors by Latent Imagination](https://mlsanity.com/paper/1912.01603/) (2019)
- [Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World](https://mlsanity.com/paper/1703.06907/) (2017)
- [Learning Latent Dynamics for Planning from Pixels](https://mlsanity.com/paper/1811.04551/) (2018)
- [Deep Reinforcement Learning in a Handful of Trials using Probabilistic Dynamics Models](https://mlsanity.com/paper/1805.12114/) (2018)
- [CURL: Contrastive Unsupervised Representations for Reinforcement Learning](https://mlsanity.com/paper/2004.04136/) (2020)
- [GPyTorch: Blackbox Matrix-Matrix Gaussian Process Inference with GPU Acceleration](https://mlsanity.com/paper/1809.11165/) (2018)
- [Deep Visual Foresight for Planning Robot Motion](https://mlsanity.com/paper/1610.00696/) (2016)
- [Visual Foresight: Model-Based Deep Reinforcement Learning for Vision-Based Robotic Control](https://mlsanity.com/paper/1812.00568/) (2018)
- [Closing the Sim-to-Real Loop: Adapting Simulation Randomization with Real World Experience](https://mlsanity.com/paper/1810.05687/) (2018)
- [Learning to Poke by Poking: Experiential Learning of Intuitive Physics](https://mlsanity.com/paper/1606.07419/) (2016)
- [Transferring End-to-End Visuomotor Control from Simulation to Real World for a Multi-Stage Task](https://mlsanity.com/paper/1707.02267/) (2017)
- [Self-Supervised Learning of State Estimation for Manipulating Deformable Linear Objects](https://mlsanity.com/paper/1911.06283/) (2019)
- [Variational Gaussian Process State-Space Models](https://mlsanity.com/paper/1406.4905/) (2014)
- [Learning Robotic Manipulation through Visual Planning and Acting](https://mlsanity.com/paper/1905.04411/) (2019)
- [Robust Locally-Linear Controllable Embedding](https://mlsanity.com/paper/1710.05373/) (2017)
- [Improvisation through Physical Understanding: Using Novel Objects as Tools with Visual Foresight](https://mlsanity.com/paper/1904.05538/) (2019)
- [Curious iLQR: Resolving Uncertainty in Model-based RL](https://mlsanity.com/paper/1904.06786/) (2019)
- [Technical Report: Safe, Aggressive Quadrotor Flight via Reachability-based Trajectory Design](https://mlsanity.com/paper/1904.05728/) (2019)
- [Learning When to Trust a Dynamics Model for Planning in Reduced State Spaces](https://mlsanity.com/paper/2001.11051/) (2020)
- [Risk Sensitive, Nonlinear Optimal Control: Iterative Linear Exponential-Quadratic Optimal Control with Gaussian Noise](https://mlsanity.com/paper/1512.07173/) (2015)

## Built on by (most cited first, 2 of 2)

- [Variational Inference MPC using Normalizing Flows and Out-of-Distribution Projection](https://mlsanity.com/paper/2205.04667/) (2022)
- [Safe Beyond the Horizon: Efficient Sampling-based MPC with Neural Control Barrier Functions](https://mlsanity.com/paper/2502.15006/) (2025)

## Abstract (arXiv)

When manipulating a novel object with complex dynamics, a state representation is not always available, for example for deformable objects. Learning both a representation and dynamics from observations requires large amounts of data. We propose Learned Visual Similarity Predictive Control (LVSPC), a novel method for data-efficient learning to control systems with complex dynamics and high-dimensional state spaces from images. LVSPC leverages a given simple model approximation from which image observations can be generated. We use these images to train a perception model that estimates the simple model state from observations of the complex system online. We then use data from the complex system to fit the parameters of the simple model and learn where this model is inaccurate, also online. Finally, we use Model Predictive Control and bias the controller away from regions where the simple model is inaccurate and thus where the controller is less reliable. We evaluate LVSPC on two tasks; manipulating a tethered mass and a rope. We find that our method performs comparably to state-of-the-art reinforcement learning methods with an order of magnitude less data. LVSPC also completes the rope manipulation task on a real robot with 80% success rate after only 10 trials, despite using a perception system trained only on images from simulation.