Deep reinforcement learning (RL) has recently shown significant benefits in solving combinatorial optimization (CO) problems, reducing reliance on domain expertise, and improving computational efficiency. However, the field lacks a unified benchmark for easy development and standardized comparison of algorithms across diverse CO problems. To fill this gap, we introduce RL4CO, a unified and extensive benchmark with in-depth library coverage of 23 state-of-the-art methods and more than 20 CO problems. Built on efficient software libraries and best practices in implementation, RL4CO features modularized implementation and flexible configuration of diverse RL algorithms, neural network architectures, inference techniques, and environments. RL4CO allows researchers to seamlessly navigate existing successes and develop their unique designs, facilitating the entire research process by decoupling science from heavy engineering. We also provide extensive benchmark studies to inspire new insights and future work. RL4CO has attracted numerous researchers in the community and is open-sourced at https://github.com/ai4co/rl4co.
RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark
Deep reinforcement learning (RL) has recently shown significant benefits in solving combinatorial optimization (CO) problems, reducing reliance on domain expertise, and improving computational efficiency.
- Year
- 2023
- Venue
- arXiv 2023
- Authors
- 33
- Hosting
- Abstract onlyARXIV-DEFAULT
Cite
Notes
Only stored in your browser.
Attribution
- Abstract & full text
- arxiv.org/abs/2306.17100v4ARXIV-DEFAULT
- TL;DR
- Semantic Scholar
Abstract
Authors
33Jie ZhangFederico BertoChuanbo HuaJunyoung ParkLaurin LuttmannYining MaFanchen BuJiarui WangHaoran YeMinsu KimSanghyeok ChoiNayeli Gast ZepedaAndré HottungJianan ZhouJieyi BiYu HuFei LiuHyeonah KimJiwoo SonHaeyeon KimDavide AngioniWouter KoolZhiguang CaoQingfu ZhangJoungho KimKijung ShinCathy WuSungsoo AhnGuojie SongChanghyun KwonKevin TierneyLin XieJinkyoo Park