Papers › RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark

RL4CO: an Extensive Reinforcement Learning for Combinatorial Optimization Benchmark

29 Jun 2023arXiv:2306.17100archive 2025-07-28

Federico Berto, Chuanbo Hua, Junyoung Park, Laurin Luttmann, Yining Ma, Fanchen Bu, Jiarui Wang, Haoran Ye, Minsu Kim, Sanghyeok Choi, Nayeli Gast Zepeda, André Hottung, Jianan Zhou, Jieyi Bi, Yu Hu, Fei Liu, Hyeonah Kim, Jiwoo Son, Haeyeon Kim, Davide Angioni, Wouter Kool, Zhiguang Cao, Qingfu Zhang, Joungho Kim, Jie Zhang, Kijung Shin, Cathy Wu, Sungsoo Ahn, Guojie Song, Changhyun Kwon, Kevin Tierney, Lin Xie, Jinkyoo Park

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.

PaperPDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2306.17100")

Code

Syntology Ran 0 of 16 code samples harvested from 2 repositories linked to this paper; 16 have no recorded run.

By repository: official repository: 13 samples from 1 repository, 0 ran; community (archive-listed): 3 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ai4co/rl4co officialmentioned in papermentioned on GitHubpytorchMIT report
pytorch/rl officialmentioned in papermentioned on GitHubjax report
facebookresearch/rl mentioned on GitHubjaxMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

16 samples harvested; 0 ran; 0 honoured the contract we drafted; 16 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

16unverified

Licence: 3 of the 16 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 2 repositories linked to this paper, official or community; each sample names its own and says which. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

batchify ai4co/rl4co/rl4co/utils/ops.py official repository unverified MIT (permissive) · e899117c9df4359e · report
clean_hydra_config ai4co/rl4co/rl4co/utils/lightning.py official repository unverified MIT (permissive) · 4f2ccb8b68f3e715 · report
create_optimizer ai4co/rl4co/rl4co/utils/optim_helpers.py official repository unverified MIT (permissive) · c30fa333f4496ccc · report
create_scheduler ai4co/rl4co/rl4co/utils/optim_helpers.py official repository unverified MIT (permissive) · e57fec3fed7f7ac3 · report
fused_chunk_linear_attn_wrapper ai4co/rl4co/rl4co/models/nn/flash_attention.py official repository unverified MIT (permissive) · 7267ff9e6a317eec · report
gather_by_index ai4co/rl4co/rl4co/utils/ops.py official repository unverified MIT (permissive) · 0fdfebdf5e82532b · report
get_lightning_device ai4co/rl4co/rl4co/utils/lightning.py official repository unverified MIT (permissive) · 8a9f41865ce393ce · report
get_log_likelihood ai4co/rl4co/rl4co/utils/decoding.py official repository unverified MIT (permissive) · a326212367641139 · report
pos_init_embedding ai4co/rl4co/rl4co/models/nn/pos_embeddings.py official repository unverified MIT (permissive) · 1ea1f47aac5e2bda · report
remove_key ai4co/rl4co/rl4co/utils/lightning.py official repository unverified MIT (permissive) · cc7ca011efea6f39 · report
scaled_dot_product_attention_flash_attn ai4co/rl4co/rl4co/models/nn/flash_attention.py official repository unverified MIT (permissive) · 59a1a205d6476e10 · report
scaled_dot_product_attention_simple ai4co/rl4co/rl4co/models/nn/attention.py official repository unverified MIT (permissive) · 247b5d1c10709554 · report
unbatchify ai4co/rl4co/rl4co/utils/ops.py official repository unverified MIT (permissive) · 83c9a91ca5c59e38 · report
prod facebookresearch/rl/torchrl/_utils.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · eb9333cd6b23461f · report
seed_generator facebookresearch/rl/torchrl/_utils.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · f82fa5a8534a7ff2 · report
strtobool facebookresearch/rl/torchrl/_utils.py community (archive-listed) unverified MIT recorded; this copy not marked cleared · pointer only · f5efb02606aa8292 · report

Tasks

Combinatorial OptimizationComputational EfficiencyDeep Reinforcement LearningManagementNavigateReinforcement LearningReinforcement Learning (RL)Traveling Salesman Problemreinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AMLSTMPOMOPointer NetworkSigmoid ActivationSoftmaxSym-NCOTanh Activation

1 archive method tag without a method page not shown.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections