# opendilab/awesome-RLHF

A curated list of reinforcement learning with human feedback resources (continually updated)

Repository: https://github.com/opendilab/awesome-RLHF
Canonical: https://ross.abutalabs.com/products/awesome-rlhf
License: Apache-2.0
License Family: permissive
Topics: deep-learning, deep-reinforcement-learning, human-feedback, reinforcement-learning, rlhf, large-language-models
Last push: 2026-05-20T12:56:15+00:00

## Health v2 (maintenance only)
Score: 68/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 83, release rhythm 35, longevity 92
- inputs: {"age_days": 1297, "days_push": 105, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 4422, forks 258 (observed 2026-08-28T04:08:48.788535+00:00)

## What it is
A curated, continually updated list of research papers, codebases, datasets, blogs, and books about Reinforcement Learning with Human Feedback (RLHF). It tracks the frontier of RLHF for both large language models and applications like video games.

## Use cases
- find papers on RLHF for LLM alignment
- learn how reinforcement learning with human feedback works
- find open-source RLHF codebases and datasets
- track the latest RLHF research in 2024-2026
- study reward modeling and human preference learning
- get reading material for aligning language models with human values

## When to choose
- you need a starting point to survey the RLHF literature
- you want curated links to papers, code, and datasets in one place
- you are researching LLM alignment or preference-based RL

## When to avoid
- you need runnable RLHF training code rather than a resource list
- you need a maintained software library with an API
- you need non-RLHF reinforcement learning resources

## Facets
- artifact type: learning-resource
- maturity: active
- function: reinforcement-learning, llm-training, machine-learning
- domain: reinforcement-learning, large-language-models, machine-learning, artificial-intelligence, tutorials
- platform: cross-platform
- tags: awesome-list, rlhf, curated-list, research-papers, human-feedback, alignment

## Member repositories
- opendilab/awesome-RLHF (main) score 68

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:08:48.788535+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-29T18:20:58.585061+00:00, confidence not recorded.
  - readme: https://github.com/opendilab/awesome-RLHF (fetched 2026-08-28T04:08:48.788535+00:00, sha 76d0ad05abfd)
- Data as of 2026-08-30T08:39:29.467469+00:00.