• Corpus ID: 233168592

Ecole: A Library for Learning Inside MILP Solvers

  title={Ecole: A Library for Learning Inside MILP Solvers},
  author={Antoine Prouvost and Justin Dumouchelle and Maxime Gasse and Didier Ch'etelat and Andrea Lodi},
In this paper we describe Ecole (Extensible Combinatorial Optimization Learning Environments), a library to facilitate integration of machine learning in combinatorial optimization solvers. It exposes sequential decision making that must be performed in the process of solving as Markov decision processes. This means that, rather than trying to predict solutions to combinatorial optimization problems directly, Ecole allows machine learning to work in cooperation with a stateof-the-art a mixed… 

Figures and Tables from this paper

ORSuite: Benchmarking Suite for Sequential Operations Models

This paper introduces ORSuite, an open-source library containing environments, algorithms, and instrumentation for operational problems, designed to motivate researchers in the reinforcement learning community to develop and evaluate algorithms on operational tasks.



Learning to Branch in Mixed Integer Programming

This work proposes a machine learning (ML) framework for variable branching in MIP, and observes the decisions made by Strong Branching, a time-consuming strategy that produces small search trees, collecting features that characterize the candidate branching variables at each node of the tree.

Learning to Search in Branch and Bound Algorithms

This work addresses the key challenge of learning an adaptive node searching order for any class of problem solvable by branch-and-bound by applying its algorithm to linear programming based branch- and-bound for solving mixed integer programs (MIP).

Exact Combinatorial Optimization with Graph Convolutional Neural Networks

A new graph convolutional neural network model is proposed for learning branch-and-bound variable selection policies, which leverages the natural variable-constraint bipartite graph representation of mixed-integer linear programs.

Parameterizing Branch-and-Bound Search Trees to Learn Branching Policies

A novel imitation learning framework is proposed, and new input features and architectures to represent branching are introduced, and the resulting policies significantly outperform the current state-of-the-art method for "learning to branch" by effectively allowing generalization to generic unseen instances.

OR-Gym: A Reinforcement Learning Library for Operations Research Problem

Reinforcement learning is applied to the knapsack, multi-dimensional bin packing,Multi-echelon supply chain, and multi-period asset allocation model problems, as well as benchmark the RL solutions against MILP and heuristic models.

Hybrid Models for Learning to Branch

This work addresses the first question in the negative, and addresses the second question by proposing a new hybrid architecture for efficient branching on CPU machines, which combines the expressive power of GNNs with computationally inexpensive multi-layer perceptrons (MLP) for branching.

A Reduction of Imitation Learning and Structured Prediction to No-Regret Online Learning

This paper proposes a new iterative algorithm, which trains a stationary deterministic policy, that can be seen as a no regret algorithm in an online learning setting and demonstrates that this new approach outperforms previous approaches on two challenging imitation learning problems and a benchmark sequence labeling problem.

Presolve Reductions in Mixed Integer Programming

The presolve functionality in the Gurobi commercial mixed-integer programming code is described, including an overview, or taxonomy, of the different methods that are employed, as well as more-detailed descriptions of several of the techniques, with some of them appearing, to the authors' knowledge, for the first time in the literature.

Automated Configuration of Mixed Integer Programming Solvers

This work studies the application of an automated algorithm configuration procedure to different MIP solvers, instance types and optimization objectives, and shows that this fully-automated process yields substantial improvements to the performance of three MIPsolvers: Cplex, Gurobi, and lpsolve.