Ecole: A Gym-like Library for Machine Learning in Combinatorial Optimization Solvers
This provides a standardized platform for researchers in combinatorial optimization to integrate machine learning more easily, though it is incremental as it builds on existing concepts like Gym.
The authors introduced Ecole, a library that simplifies machine learning research for combinatorial optimization by exposing decision tasks in solvers as control problems over Markov decision processes, with an interface mimicking OpenAI Gym to lower entry barriers and accelerate innovation.
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.