Papers › Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays

Boosting Reinforcement Learning with Strongly Delayed Feedback Through Auxiliary Short Delays

5 Feb 2024arXiv:2402.03141archive 2025-07-28

Qingyuan Wu, Simon Sinong Zhan, YiXuan Wang, Yuhui Wang, Chung-Wei Lin, Chen Lv, Qi Zhu, Jürgen Schmidhuber, Chao Huang

Reinforcement learning (RL) is challenging in the common case of delays between events and their sensory perceptions. State-of-the-art (SOTA) state augmentation techniques either suffer from state space explosion or performance degeneration in stochastic environments. To address these challenges, we present a novel Auxiliary-Delayed Reinforcement Learning (AD-RL) method that leverages auxiliary tasks involving short delays to accelerate RL with long delays, without compromising performance in stochastic environments. Specifically, AD-RL learns a value function for short delays and uses bootstrapping and policy improvement techniques to adjust it for long delays. We theoretically show that this can greatly reduce the sample complexity. On deterministic and stochastic benchmarks, our method significantly outperforms the SOTAs in both sample efficiency and policy performance. Code is available at https://github.com/QingyuanWuNothing/AD-RL.

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 11 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 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 1 repository, 10 ran (8 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 10 samples that ran has no recorded date.

qingyuanwunothing/ad-rl officialmentioned in paperpytorchSyntology: 11 samples, 10 ran (2 instrument-failed) · 1 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: 10 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 2 where Syntology's instrument failed) · 1 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.

1ran · honoured contract
1ran · our draft was wrong
1ran; the contract check could not run
7ran
1unverified

Licence: 11 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 qingyuanwunothing/ad-rl. “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.

qingyuanwunothing/ad-rl official repository 11 samples, 10 ran (2 instrument-failed) · 1 unverified
action_value DETERMINISTIC-MDP.py ran no licence file found · pointer only · d27cd46bef9cd5a7 · report fixture: signature Q_VALUE:dict/0/?, STATE:int/0/int, ACTION:int/0/int · returned float · level recorded 2026-09-24
find_specific_exp_tag utils.py ran no licence file found · pointer only · 8d481d190b83d758 · report fixture: signature exp_dict:str/0/str, exp_tag:str/0/str · returned bool · level recorded 2026-09-24
greedy_action DETERMINISTIC-MDP.py ran · honoured contract no licence file found · pointer only · 4562c1fef99e80f7 · report fixture: signature Q_VALUE:dict/0/?, STATE:int/0/int · returned int · level recorded 2026-09-24
layer_init in 46 papers nn.py ran · our draft was wrong no licence file found · pointer only · beb42d440ccf2925 · report fixture: signature layer:callable/0/?, std:float/0/float, bias_const:float/0/float · returned Linear · level recorded, date not recorded
make_anneal_lr utils.py ran fingerprinted no licence file found · pointer only · c21517332c327b92 · report fixture: signature update:int/0/int, num_updates:int/0/int, lr:float/0/float · returned float · level recorded 2026-09-24
make_classical_env make_env.py ran no licence file found · pointer only · 7c5acb79755772b3 · report fixture: signature env_id:str/0/str, seed:int/0/int · returned function · level recorded 2026-09-24
make_classical_obs_delay_env make_env.py ran no licence file found · pointer only · 954a62d688488366 · report fixture: signature env_id:str/0/str, seed:int/0/int, max_obs_delay_step:int/0/int · returned function · level recorded 2026-09-24
make_linear_schedule utils.py ran fingerprinted no licence file found · pointer only · bdf1781d7265fc58 · report fixture: signature start:float/0/float, end:float/0/float, duration:int/0/int, t:int/0/int · returned float · level recorded 2026-09-24
make_vector_classical_envs make_env.py ran no licence file found · pointer only · af3f16c8beef0513 · report fixture: signature env_id:str/0/str, num_envs:int/0/int, seed:int/0/int · returned SyncVectorEnv · level recorded 2026-09-24
step in 32 papers DETERMINISTIC-MDP.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 6abe638592f2fc98 · report fixture: signature STATE:tuple/1/int, ACTION:int/0/int · returned tuple · level recorded 2026-09-24
ReplayBuffer in 33 papers AD-DQN.py unverified no licence file found · pointer only · 68200fece3c9d915 · report

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 Auxiliary-Delayed Reinforcement Learning (AD-RL) (graph method: Auxiliary-Delayed Reinforcement Learning (AD-RL)). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

  1. ReplayBuffer entry · level 0 · unverified · 68200fece3c9d915

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="2402.03141") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Reinforcement 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