# huawei-noah/HEBO

Bayesian optimisation & Reinforcement Learning library developed by Huawei Noah's Ark Lab

Repository: https://github.com/huawei-noah/HEBO
Canonical: https://ross.abutalabs.com/products/hebo
Language: Jupyter Notebook
License Family: other
Last push: 2026-01-31T14:04:23+00:00

## Health v2 (maintenance only)
Score: 52/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 65, release rhythm 8, longevity 100
- inputs: {"age_days": 1818, "days_push": 214, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 2797, forks 472 (observed 2026-08-28T04:07:22.455003+00:00)

## What it is
A research monorepo from Huawei Noah's Ark Lab containing official implementations of Bayesian optimization, reinforcement learning, and generative model projects. Its flagship HEBO library is a heteroscedastic evolutionary Bayesian optimization package that won the NeurIPS 2020 Black-Box Optimisation Challenge.

## Use cases
- optimize hyperparameters of machine learning models
- black-box optimization of expensive functions
- combinatorial and mixed-variable Bayesian optimization
- high-dimensional Bayesian optimization
- safe reinforcement learning experiments
- offline reinforcement learning research
- antibody design with Bayesian optimization

## When to choose
- you need a proven, competition-winning Bayesian optimization library in Python
- you want research-grade implementations of recent BO and RL papers
- your optimization problem has mixed or combinatorial variables

## When to avoid
- you need a permissively licensed dependency - the repo has no explicit license
- you need production-hardened, well-documented tooling rather than research code
- you want a general-purpose ML framework rather than an optimization library

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, reinforcement-learning, benchmarking
- domain: machine-learning, artificial-intelligence
- platform: python, cross-platform
- tags: bayesian-optimization, hyperparameter-optimization, black-box-optimization, reinforcement-learning, generative-models, research-code, algorithms, research

## Member repositories
- huawei-noah/HEBO (main) score 52

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:22.455003+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 2026-08-29T18:49:04.673708+00:00, confidence not recorded.
  - readme: https://github.com/huawei-noah/HEBO (fetched 2026-08-28T04:07:22.455003+00:00, sha 4e8681259e71)
  - registry_pypi: https://pypi.org/pypi/hebo/json (fetched 2026-08-29T09:54:47.839362+00:00, sha c7995ef6f636)
- Data as of 2026-08-30T08:39:29.467469+00:00.