Papers › NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in...

NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation

30 Oct 2024arXiv:2411.04138archive 2025-07-28

Momin Haider, Ming Yin, Menglei Zhang, Arpit Gupta, Jing Zhu, Yu-Xiang Wang

Mobile devices such as smartphones, laptops, and tablets can often connect to multiple access networks (e.g., Wi-Fi, LTE, and 5G) simultaneously. Recent advancements facilitate seamless integration of these connections below the transport layer, enhancing the experience for apps that lack inherent multi-path support. This optimization hinges on dynamically determining the traffic distribution across networks for each device, a process referred to as multi-access traffic splitting. This paper introduces NetworkGym, a high-fidelity network environment simulator that facilitates generating multiple network traffic flows and multi-access traffic splitting. This simulator facilitates training and evaluating different RL-based solutions for the multi-access traffic splitting problem. Our initial explorations demonstrate that the majority of existing state-of-the-art offline RL algorithms (e.g. CQL) fail to outperform certain hand-crafted heuristic policies on average. This illustrates the urgent need to evaluate offline RL algorithms against a broader range of benchmarks, rather than relying solely on popular ones such as D4RL. We also propose an extension to the TD3+BC algorithm, named Pessimistic TD3 (PTD3), and demonstrate that it outperforms many state-of-the-art offline RL algorithms. PTD3's behavioral constraint mechanism, which relies on value-function pessimism, is theoretically motivated and relatively simple to implement.

PaperPDFCodeCode Syntology ranMethod as code

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

Syntology 18 code samples harvested from 2 repositories linked to this paper: 15 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 6 ran (5 with no instrument failure; 1 where Syntology's instrument failed); found in paper text by Syntology: 9 samples from 1 repository, 9 ran (2 with no instrument failure; 7 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 4 of the 15 samples that ran have no recorded date.

hmomin/networkgym officialpytorchSyntology: 9 samples, 6 ran (1 instrument-failed) · 3 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

18 samples harvested: 15 ran (of which 2 constructed an object rather than computing a result; 7 with no instrument failure: 4 honoured, 0 violated, 3 with no contract checked; 8 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · honoured contract
5ran · our draft was wrong
3ran; the contract check could not run
3ran
3unverified

Licence: 1 of the 18 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. 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; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

hmomin/networkgym official repository 9 samples, 6 ran (1 instrument-failed) · 3 unverified
Buffer in 23 papers NetworkAgent/ptd3/agent.py ran Apache-2.0 (permissive) · 5364f4044a619e47 · report fixture: returned Buffer · level recorded 2026-09-22
MLP in 375 papers NetworkAgent/ptd3/agent.py ran fingerprinted Apache-2.0 (permissive) · d7ae5ebb17778665 · report fixture: returned MLP · level recorded 2026-09-22
Sherman_Morrison_inverse NetworkAgent/ptd3/agent.py ran · honoured contract Apache-2.0 (permissive) · 38e93fb6353025b8 · report fixture: signature A_inverse:Tensor/2/float, u:Tensor/2/float, v:Tensor/2/float · returned Tensor · level recorded, date not recorded
get_num_parameters_from_matrix NetworkAgent/ptd3/agent.py ran · honoured contract Apache-2.0 (permissive) · 3e80cb315de8ba69 · report fixture: signature param:Tensor/4/float · returned int · level recorded 2026-09-22
safe_concat NetworkAgent/ptd3/agent.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · 835cbe687de8fb40 · report fixture: signature array_1:ndarray/2/int, array_2:ndarray/2/int, max_size:int/0/int · returned ndarray · level recorded 2026-09-22
safe_stack NetworkAgent/ptd3/agent.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · 26f75cae6942c75c · report fixture: signature array_1:ndarray/2/float, array_2:ndarray/2/int · returned ndarray · level recorded 2026-09-22
CombinedBuffer NetworkAgent/ptd3/agent.py unverified Apache-2.0 (permissive) · 9f18e9c6c8c3eb47 · report
OfflineEnv NetworkAgent/ptd3/agent.py unverified Apache-2.0 (permissive) · b1d7b6c14279e8ed · report
PessimisticTD3 NetworkAgent/ptd3/agent.py unverified Apache-2.0 (permissive) · 3a9e7d766c9d5bef · report
hmomin/CORL-compare found in paper text by Syntology 9 samples, 9 ran (7 instrument-failed) · 0 unverified
compute_mean_std in 20 papers algorithms/finetune/awac.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 4e08ac58e3891cfb · report fixture: signature states:ndarray/2/float, eps:float/0/float · returned tuple · level recorded, date not recorded
compute_mean_std in 20 papers algorithms/finetune/iql.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 639b4986c270df90 · report fixture: signature states:ndarray/2/float, eps:float/0/float · returned tuple · level recorded, date not recorded
get_average_scores results/get_finetune_tables_and_plots.py ran · our draft was wrong Apache-2.0 (permissive) · e482b76be0b40fe2 · report fixture: signature scores:dict/0/? · returned tuple · level recorded 2026-09-25
get_last_scores results/get_finetune_tables_and_plots.py ran · our draft was wrong Apache-2.0 (permissive) · 8cee6cb43695037e · report fixture: signature avg_scores:dict/0/?, avg_stds:dict/0/? · returned tuple · level recorded 2026-09-25
get_max_scores results/get_finetune_tables_and_plots.py ran · our draft was wrong Apache-2.0 (permissive) · b55784199eb66664 · report fixture: signature scores:dict/0/? · returned tuple · level recorded 2026-09-25
normalize_states in 15 papers algorithms/finetune/awac.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · ba80f9ff81b1de5f · report fixture: signature states:ndarray/2/float, mean:ndarray/1/float, std:ndarray/1/float · returned ndarray · level recorded, date not recorded
wrap_env in 9 papers algorithms/finetune/awac.py ran Apache-2.0 (permissive) · 80f4da28d1c7ef4f · report fixture: signature env:TimeLimit/0/?, state_mean:ndarray/1/float, state_std:ndarray/1/float · returned TransformObservation · level recorded 2026-09-25
wrap_env in 9 papers algorithms/finetune/cal_ql.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · 4dd56ecf0f797666 · report fixture: signature env:TimeLimit/0/?, state_mean:ndarray/1/float, state_std:ndarray/1/float, reward_scale:float/0/float · returned TransformReward · level recorded 2026-09-25
wrap_env in 9 papers algorithms/finetune/iql.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · a8341f5e34d50ae6 · report fixture: signature env:TimeLimit/0/?, state_mean:ndarray/1/float, state_std:ndarray/1/float, reward_scale:float/0/float · returned TransformReward · level recorded 2026-09-25

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.

1 assembly on this paper: 1 harvested, 0 generated.

harvested Assembly for Pessimistic TD3 (PTD3) (graph method: Pessimistic TD3 (PTD3)). 9 bricks; individually on a fixture: 6 ran (of which 2 constructed an object rather than computing a result; 5 with no instrument failure: 3 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

  1. PessimisticTD3 entry · level 0 · unverified · 3a9e7d766c9d5bef
  2. CombinedBuffer helper · level 0 · unverified · 9f18e9c6c8c3eb47
  3. MLP helper · level 1 · ran · d7ae5ebb17778665
  4. OfflineEnv helper · level 0 · unverified · b1d7b6c14279e8ed
  5. Sherman_Morrison_inverse helper · level 1 · ran · honoured contract · 38e93fb6353025b8
  6. Buffer helper · level 1 · ran · 5364f4044a619e47
  7. safe_concat helper · level 1 · ran; the contract check could not run (RAISES) · 835cbe687de8fb40
  8. get_num_parameters_from_matrix helper · level 1 · ran · honoured contract · 3e80cb315de8ba69
  9. safe_stack helper · level 1 · ran · honoured contract · 26f75cae6942c75c

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2411.04138") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

D4RLManagementOffline RL

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamClipped Double Q-learningDense ConnectionsExperience ReplayReLUTD3Target Policy Smoothing

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