Papers › AGaLiTe: Approximate Gated Linear Transformers for Online Reinforcement Learning

AGaLiTe: Approximate Gated Linear Transformers for Online Reinforcement Learning

24 Oct 2023arXiv:2310.15719archive 2025-07-28

Subhojeet Pramanik, Esraa Elelimy, Marlos C. Machado, Adam White

In this paper we investigate transformer architectures designed for partially observable online reinforcement learning. The self-attention mechanism in the transformer architecture is capable of capturing long-range dependencies and it is the main reason behind its effectiveness in processing sequential data. Nevertheless, despite their success, transformers have two significant drawbacks that still limit their applicability in online reinforcement learning: (1) in order to remember all past information, the self-attention mechanism requires access to the whole history to be provided as context. (2) The inference cost in transformers is expensive. In this paper, we introduce recurrent alternatives to the transformer self-attention mechanism that offer context-independent inference cost, leverage long-range dependencies effectively, and performs well in online reinforcement learning task. We quantify the impact of the different components of our architecture in a diagnostic environment and assess performance gains in 2D and 3D pixel-based partially-observable environments (e.g. T-Maze, Mystery Path, Craftax, and Memory Maze). Compared with a state-of-the-art architecture, GTrXL, inference in our approach is at least 40% cheaper while reducing memory use more than 50%. Our approach either performs similarly or better than GTrXL, improving more than 37% upon GTrXL performance in harder tasks.

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

Syntology 11 code samples harvested from 2 repositories linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 11 samples from 2 repositories, 7 ran (5 with no instrument failure; 2 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

subho406/Recurrent-Linear-Transformers officialmentioned in papermentioned on GitHubjaxApache-2.0Syntology: 6 samples, 4 ran (0 instrument-failed) · 2 unverified report
subho406/agalite officialjaxSyntology: 5 samples, 3 ran (2 instrument-failed) · 2 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

11 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 0 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 4 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.

1ran · honoured contract
1ran · our draft was wrong
1ran; the contract check could not run
4ran
4unverified

Licence: 0 of the 11 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; 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”. “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.

subho406/Recurrent-Linear-Transformers official repository 6 samples, 4 ran (0 instrument-failed) · 2 unverified
actor_model_discete src/model_fns/achead_fns.py ran Apache-2.0 (permissive) · 3794764640830e25 · report fixture: signature dense_dim:int/0/int, action_space:int/0/int · returned function · level recorded 2026-09-24
critic_model src/model_fns/achead_fns.py ran Apache-2.0 (permissive) · 85f1e371fbe56d2c · report fixture: signature dense_dim:int/0/int · returned function · level recorded 2026-09-24
jax_pad src/utils.py ran Apache-2.0 (permissive) · 99c1d0c4eabda3cc · report fixture: signature input:ArrayImpl/3/float, pad:tuple/1/int, mode:str/0/str, value:int/0/int · returned ArrayImpl · level recorded 2026-09-24
masked_fill src/utils.py ran Apache-2.0 (permissive) · 04c4ac86fa07622e · report fixture: signature mask:ArrayImpl/2/bool, a:ArrayImpl/2/float, fill:float/0/float · returned ArrayImpl · level recorded 2026-09-24
main in 235 papers trainer_pure.py unverified Apache-2.0 (permissive) · 10be38ccb17045ea · report
tree_dot src/utils.py unverified Apache-2.0 (permissive) · c63da903ea6731df · report
subho406/agalite official repository 5 samples, 3 ran (2 instrument-failed) · 2 unverified
binary_operator in 10 papers src/models/agalite/agalite.py ran; the contract check could not run (RAISES) · metamorphic tier: well formed fingerprinted Apache-2.0 (permissive) · ed42d985a78a9d09 · report fixture: signature x:tuple/1/Tensor, y:tuple/1/Tensor · returned tuple · level recorded 2026-09-22
dpfp src_pure/models/agalite.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 93e29f94d7e078ff · report fixture: signature x:ArrayImpl/2/float, nu:int/0/int · returned ArrayImpl · level recorded 2026-09-22
kernel_config_to_output_dim src_pure/models/agalite.py ran · honoured contract Apache-2.0 (permissive) · 4ebe8a74c4714481 · report fixture: signature dim:int/0/int, kernel_config:dict/0/? · returned int · level recorded 2026-09-22
discounted_sum_jax src/models/agalite/agalite.py unverified Apache-2.0 (permissive) · 89290db1912cbf52 · report
discounted_sum_parallel src/models/agalite/agalite.py unverified Apache-2.0 (permissive) · 52da6b9a0a2cbffe · report

Tasks

DiagnosticReinforcement Learningreinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AttentionDense ConnectionsGRUGTrXLLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerSoftmax

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