Papers › Exploratory Combinatorial Optimization with Reinforcement Learning

Exploratory Combinatorial Optimization with Reinforcement Learning

9 Sep 2019arXiv:1909.04063archive 2025-07-28

Thomas D. Barrett, William R. Clements, Jakob N. Foerster, A. I. Lvovsky

Many real-world problems can be reduced to combinatorial optimization on a graph, where the subset or ordering of vertices that maximize some objective function must be found. With such tasks often NP-hard and analytically intractable, reinforcement learning (RL) has shown promise as a framework with which efficient heuristic methods to tackle these problems can be learned. Previous works construct the solution subset incrementally, adding one element at a time, however, the irreversible nature of this approach prevents the agent from revising its earlier decisions, which may be necessary given the complexity of the optimization task. We instead propose that the agent should seek to continuously improve the solution by learning to explore at test time. Our approach of exploratory combinatorial optimization (ECO-DQN) is, in principle, applicable to any combinatorial problem that can be defined on a graph. Experimentally, we show our method to produce state-of-the-art RL performance on the Maximum Cut problem. Moreover, because ECO-DQN can start from any arbitrary configuration, it can be combined with other search methods to further improve performance, which we demonstrate using a simple random search.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

The archive's official repository (tomdbar/eco-dqn) was not harvested; the 20 samples below come from 1 community repository.

Syntology 20 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 20 samples from 1 repository, 10 ran (10 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

tomdbar/eco-dqn officialmentioned in papermentioned on GitHubpytorchMITSyntology: not harvested report
ilBarbara/BioRL mentioned on GitHubpytorchMITSyntology: 20 samples, 10 ran (0 instrument-failed) · 10 unverified 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

20 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 10 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

10ran
10unverified

Licence: 0 of the 20 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 ilBarbara/BioRL. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

ilBarbara/BioRL community (archive-listed) 20 samples, 10 ran (0 instrument-failed) · 10 unverified
adj_dict_to_lists src/comet/mutation_data.py ran MIT (permissive) · ebb92c545dd37c5e · report fixture: signature xs:list/1/str, ys:list/1/str, d:dict/0/? · returned list · level recorded 2026-09-24
call_multidendrix src/comet/utils.py ran MIT (permissive) · e3297cca27fd41f9 · report fixture: signature multi_dendrix:MockMultiDendrix/0/?, mutations:dict/0/?, k:int/0/int, t:int/0/int · returned list · level recorded 2026-09-24
compute_edge_dist src/comet/output.py ran MIT (permissive) · 6fddb61386269dbe · report fixture: signature G:Graph/0/?, deltas:ndarray/1/float · returned ndarray · level recorded 2026-09-24
convert_mutations_to_C_format src/comet/mutation_data.py ran MIT (permissive) · b54eb9d11c17ff7b · report fixture: signature m:int/0/int, n:int/0/int, genes:list/1/str, patients:list/1/str, geneToCases:dict/0/?, patientToGenes:dict/0/?, subtypes:NoneType/0/? · returned tuple · level recorded 2026-09-24
convert_solns src/comet/utils.py ran MIT (permissive) · 646d9fed47dadc7e · report fixture: signature indexToGene:dict/0/?, solns:list/1/list · returned list · level recorded 2026-09-24
graph_to_mutation_data src/comet/permute.py ran MIT (permissive) · a388b8293614beeb · report fixture: signature H:dict/0/?, genes:list/1/str, patients:list/1/str · returned tuple · level recorded 2026-09-24
iter_num src/comet/output.py ran MIT (permissive) · 41514aa1cf823b3e · report fixture: signature prefix:str/0/str, numIters:float/0/float, ks:list/1/int, acc:float/0/float · returned str · level recorded 2026-09-24
load_graph in 36 papers experiments/utils.py ran MIT (permissive) · 159da52928b75420 · report fixture: signature graph_dir:str/0/str, graph_name:str/0/str · returned Graph · level recorded 2026-09-24
load_graph_set experiments/utils.py ran MIT (permissive) · 9887ce2dbe863145 · report fixture: signature graph_save_loc:str/0/str · returned list · level recorded 2026-09-24
tv src/comet/convergence.py ran fingerprinted MIT (permissive) · b28a2a9a7ba12564 · report fixture: signature p:list/1/float, q:list/1/float · returned float · level recorded 2026-09-24
bipartite_double_edge_swap src/comet/permute.py unverified MIT (permissive) · cd32e999ec66db43 · report
check_condition src/envs/saddlepoint.py unverified MIT (permissive) · cd51a1fc23564cb6 · report
choose_delta src/comet/output.py unverified MIT (permissive) · 0b789d75b024c791 · report
construct_mutation_graph src/comet/permute.py unverified MIT (permissive) · d56306f4d27a55b3 · report
discrete_convergence src/comet/convergence.py unverified MIT (permissive) · d3c7bc0639c710a4 · report
discrete_convergence_eqb_plot src/comet/convergence.py unverified MIT (permissive) · 3a84f2cd9eb58674 · report
enumeration src/envs/saddlepoint.py unverified MIT (permissive) · ba02410b1835f606 · report
initial_solns_generator src/comet/utils.py unverified MIT (permissive) · 204686180f489e85 · report
load_mutation_data src/comet/mutation_data.py unverified MIT (permissive) · 9e0d20c4942bc700 · report
saddlepoint src/envs/saddlepoint.py unverified MIT (permissive) · f1deba67bc27ecef · report

Tasks

Combinatorial OptimizationReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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