Papers › Quality Diversity through Human Feedback: Towards Open-Ended Diversity-Driven Optimization

Quality Diversity through Human Feedback: Towards Open-Ended Diversity-Driven Optimization

18 Oct 2023arXiv:2310.12103archive 2025-07-28

Li Ding, Jenny Zhang, Jeff Clune, Lee Spector, Joel Lehman

Reinforcement Learning from Human Feedback (RLHF) has shown potential in qualitative tasks where easily defined performance measures are lacking. However, there are drawbacks when RLHF is commonly used to optimize for average human preferences, especially in generative tasks that demand diverse model responses. Meanwhile, Quality Diversity (QD) algorithms excel at identifying diverse and high-quality solutions but often rely on manually crafted diversity metrics. This paper introduces Quality Diversity through Human Feedback (QDHF), a novel approach that progressively infers diversity metrics from human judgments of similarity among solutions, thereby enhancing the applicability and effectiveness of QD algorithms in complex and open-ended domains. Empirical studies show that QDHF significantly outperforms state-of-the-art methods in automatic diversity discovery and matches the efficacy of QD with manually crafted diversity metrics on standard benchmarks in robotics and reinforcement learning. Notably, in open-ended generative tasks, QDHF substantially enhances the diversity of text-to-image generation from a diffusion model and is more favorably received in user studies. We conclude by analyzing QDHF's scalability, robustness, and quality of derived diversity metrics, emphasizing its strength in open-ended optimization tasks. Code and tutorials are available at https://liding.info/qdhf.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="2310.12103")

Code

Syntology Ran 7 of 7 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 7 ran with no contract checked.

By repository: official repository: 7 samples from 1 repository, 7 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

ld-ing/qdhf officialmentioned in papermentioned on GitHubjaxMIT 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; 7 ran; 0 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

7ran

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 ld-ing/qdhf. “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.

fit_ae ld-ing/qdhf/arm/utils.py official repository ran MIT (permissive) · cc9d79fa0ef76213 · report
fit_ae ld-ing/qdhf/lsi/lsi_utils.py official repository ran MIT (permissive) · 04b894983e853cbb · report
fit_ae ld-ing/qdhf/maze/utils.py official repository ran MIT (permissive) · 9379db3f2290a2ae · report
fit_dis_embed ld-ing/qdhf/arm/utils.py official repository ran MIT (permissive) · bc5b03184ad01f17 · report
fit_dis_embed ld-ing/qdhf/lsi/lsi_utils.py official repository ran MIT (permissive) · 9847b9196dde5a2e · report
fit_dis_embed ld-ing/qdhf/maze/utils.py official repository ran MIT (permissive) · e36b31f563696ee5 · report
fit_pca ld-ing/qdhf/arm/utils.py official repository ran MIT (permissive) · bc38843352b4eff1 · report

Tasks

DiversityImage GenerationReinforcement LearningReinforcement Learning (RL)Robotic GraspingText to Image GenerationText-to-Image Generationreinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Diffusion

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