# CoCo: Online Mixed-Integer Control via Supervised Learning

arXiv: https://arxiv.org/abs/2107.08143 · HTML: https://mlsanity.com/paper/2107.08143/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jul 2021.

## Built on by (most cited first, 16 of 16)

- [Tutorial on amortized optimization](https://mlsanity.com/paper/2202.00665/) (2022)
- [DiffuSolve: Diffusion-based Solver for Non-convex Trajectory Optimization](https://mlsanity.com/paper/2403.05571/) (2024)
- [A Survey of Optimization-based Task and Motion Planning: From Classical To Learning Approaches](https://mlsanity.com/paper/2404.02817/) (2024)
- [Amortized Global Search for Efficient Preliminary Trajectory Design with Deep Generative Models](https://mlsanity.com/paper/2308.03960/) (2023)
- [Towards Robust Spacecraft Trajectory Optimization via Transformers](https://mlsanity.com/paper/2410.05585/) (2024)
- [Learning to Optimize for Mixed-Integer Non-linear Programming with Feasibility Guarantees](https://mlsanity.com/paper/2410.11061/) (2024)
- [Learning-Guided Rolling Horizon Optimization for Long-Horizon Flexible Job-Shop Scheduling](https://mlsanity.com/paper/2502.15791/) (2025)
- [Deep Learning Warm Starts for Trajectory Optimization on the International Space Station](https://mlsanity.com/paper/2505.05588/) (2025)
- [A Machine Learning Approach to Two-Stage Adaptive Robust Optimization](https://mlsanity.com/paper/2307.12409/) (2023)
- [Differentiable Cutting-plane Layers for Mixed-integer Linear Optimization](https://mlsanity.com/paper/2311.03350/) (2023)
- [Compositional Diffusion Models for Powered Descent Trajectory Generation with Flexible Constraints](https://mlsanity.com/paper/2410.04261/) (2024)
- [Optimal Control of Multiclass Fluid Queueing Networks: A Machine Learning Approach](https://mlsanity.com/paper/2307.12405/) (2023)
- [Integrating Reinforcement Learning and Model Predictive Control with Applications to Microgrids](https://mlsanity.com/paper/2409.11267/) (2024)
- [GLENS: Global Search via Learning from Solver Iterates with Diffusion Models](https://mlsanity.com/paper/2606.00366/) (2026)
- [Tight Constraint Prediction of Six-Degree-of-Freedom Transformer-based Powered Descent Guidance](https://mlsanity.com/paper/2501.00930/) (2025)
- [Mixed-Integer Nonlinear Differentiable Predictive Control for Underground Pumped Hydro Energy Storage Systems](https://mlsanity.com/paper/2609.17964/) (2026)

## Abstract (arXiv)

Many robotics problems, from robot motion planning to object manipulation, can be modeled as mixed-integer convex programs (MICPs). However, state-of-the-art algorithms are still unable to solve MICPs for control problems quickly enough for online use and existing heuristics can typically only find suboptimal solutions that might degrade robot performance. In this work, we turn to data-driven methods and present the Combinatorial Offline, Convex Online (CoCo) algorithm for quickly finding high quality solutions for MICPs. CoCo consists of a two-stage approach. In the offline phase, we train a neural network classifier that maps the problem parameters to a (logical strategy), which we define as the discrete arguments and relaxed big-M constraints associated with the optimal solution for that problem. Online, the classifier is applied to select a candidate logical strategy given new problem parameters; applying this logical strategy allows us to solve the original MICP as a convex optimization problem. We show through numerical experiments how CoCo finds near optimal solutions to MICPs arising in robot planning and control with 1 to 2 orders of magnitude solution speedup compared to other data-driven approaches and solvers.