Papers › Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence...

Reliability and Learnability of Human Bandit Feedback for Sequence-to-Sequence Reinforcement Learning

27 May 2018ACL 2018 7arXiv:1805.10627archive 2025-07-28

Julia Kreutzer, Joshua Uyheng, Stefan Riezler

We present a study on reinforcement learning (RL) from human bandit feedback for sequence-to-sequence learning, exemplified by the task of bandit neural machine translation (NMT). We investigate the reliability of human bandit feedback, and analyze the influence of reliability on the learnability of a reward estimator, and the effect of the quality of reward estimates on the overall RL task. Our analysis of cardinal (5-point ratings) and ordinal (pairwise preferences) feedback shows that their intra- and inter-annotator α-agreement is comparable. Best reliability is obtained for standardized cardinal feedback, and cardinal feedback is also easiest to learn and generalize from. Finally, improvements of over 1 BLEU can be obtained by integrating a regression-based reward estimator trained on cardinal feedback for 800 translations into RL for NMT. This shows that RL is possible even from small amounts of fairly reliable human feedback, pointing to a great potential for applications at larger scale.

PaperPDFConference PDFCodeCode 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="1805.10627")

Code

Syntology Ran 0 of 7 code samples harvested from 1 repository linked to this paper; 7 have no recorded run.

By repository: named in the paper: 7 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.

juliakreutzer/bandit-neuralmonkey mentioned in papertfBSD-3-Clause 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

7 samples harvested; 0 ran; 0 honoured the contract we drafted; 7 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.

7unverified

Licence: 0 of the 7 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 juliakreutzer/bandit-neuralmonkey. “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.

evaluation juliakreutzer/bandit-neuralmonkey/neuralmonkey/learning_utils.py named in the paper unverified BSD-3-Clause (permissive) · 4702de42b8eb5525 · report
get_resnet_by_type juliakreutzer/bandit-neuralmonkey/neuralmonkey/encoders/imagenet_encoder.py named in the paper unverified BSD-3-Clause (permissive) · ee48d09163d7e0f8 · report
get_vgg_by_type juliakreutzer/bandit-neuralmonkey/neuralmonkey/encoders/imagenet_encoder.py named in the paper unverified BSD-3-Clause (permissive) · e505daf00e73c61d · report
inverse_sigmoid_decay juliakreutzer/bandit-neuralmonkey/neuralmonkey/functions.py named in the paper unverified BSD-3-Clause (permissive) · 496fbab08f298f24 · report
noam_decay juliakreutzer/bandit-neuralmonkey/neuralmonkey/functions.py named in the paper unverified BSD-3-Clause (permissive) · 04265eb4f7053b66 · report
piecewise_function juliakreutzer/bandit-neuralmonkey/neuralmonkey/functions.py named in the paper unverified BSD-3-Clause (permissive) · 75f62c423690e313 · report
reinforce_score juliakreutzer/bandit-neuralmonkey/neuralmonkey/trainers/bandit_trainer.py named in the paper unverified BSD-3-Clause (permissive) · e271b362c4222cd1 · report

Tasks

Machine TranslationNMTReinforcement LearningReinforcement Learning (RL)Translationreinforcement-learning

Datasets

Introduced by this paper, per the archive.

HumanMT

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