Ecole: A Gym-like Library for Machine Learning in Combinatorial Optimization Solvers
arXiv:2011.06069
Abstract
We present Ecole, a new library to simplify machine learning research for combinatorial optimization. Ecole exposes several key decision tasks arising in general-purpose combinatorial optimization solvers as control problems over Markov decision processes. Its interface mimics the popular OpenAI Gym library and is both extensible and intuitive to use. We aim at making this library a standardized platform that will lower the bar of entry and accelerate innovation in the field. Documentation and code can be found at https://www.ecole.ai.
Published at the 1st Workshop on Learning Meets Combinatorial Algorithms @ NeurIPS 2020, Vancouver, Canada
References in corpus (9)
- The NumPy array: a structure for efficient numerical computation
- Learning Combinatorial Optimization Algorithms over Graphs
- Neural Combinatorial Optimization with Reinforcement Learning
- Attention, Learn to Solve Routing Problems!
- Hybrid Models for Learning to Branch
- A Study of Learning Search Approximation in Mixed Integer Branch and Bound: Node Selection in SCIP
- Learning to Search via Retrospective Imitation
- Accelerating Primal Solution Findings for Mixed Integer Programs Based on Solution Prediction
- Cuts, Primal Heuristics, and Learning to Branch for the Time-Dependent Traveling Salesman Problem