@misc{BertoHuaParketal., author = {Berto, Federico and Hua, Chuanbo and Park, Junyoung and Luttmann, Laurin and Ma, Yining and Bu, Fanchen and Wang, Jiarui and Ye, Haoran and Kim, Minsu and Choi, Sanghyeok and Zepeda, Nayeli Gast and Hottung, Andr{\´e} and Zhou, Jianan and Bi, Jieyi and Hu, Yu and Liu, Fei and Kim, Hyeonah and Son, Jiwoo and Kim, Haeyeon and Angioni, Davide and Kool, Wouter and Cao, Zhiguang and Zhang, Qingfu and Kim, Joungho and Zhang, Jie and Shin, Kijung and Wu, Cathy and Ahn, Sungsoo and Song, Guojie and Kwon, Changhyun and Tierney, Kevin and Xie, Lin and Park, Jinkyoo}, title = {RL4CO : an extensive reinforcement learning for combinatorial optimization benchmark}, series = {KDD '25 : proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2}, journal = {KDD '25 : proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2}, publisher = {ACM}, address = {New York, NY, USA}, isbn = {979-8-4007-1454-2}, doi = {10.1145/3711896.3737433}, pages = {5278 -- 5289}, abstract = {Combinatorial optimization (CO) is fundamental to several real-world applications, from logistics and scheduling to hardware design and resource allocation. Deep reinforcement learning (RL) has recently shown significant benefits in solving CO problems, reducing reliance on domain expertise and improving computational efficiency. However, the absence of a unified benchmarking framework leads to inconsistent evaluations, limits reproducibility, and increases engineering overhead, raising barriers to adoption for new researchers. To address these challenges, we introduce RL4CO, a unified and extensive benchmark with in-depth library coverage of 27 CO problem environments and 23 state-of-the-art baselines. Built on efficient software libraries and best practices in implementation, RL4CO features modularized implementation and flexible configurations of diverse environments, policy architectures, RL algorithms, and utilities with extensive documentation. RL4CO helps researchers build on existing successes while exploring and developing their own designs, facilitating the entire research process by decoupling science from heavy engineering. We finally provide extensive benchmark studies to inspire new insights and future work. RL4CO has already attracted numerous researchers in the community and is open-sourced at https://github.com/ai4co/rl4co.}, language = {en} }