# google/brain-tokyo-workshop

🧠🗼

Repository: https://github.com/google/brain-tokyo-workshop
Canonical: https://ross.abutalabs.com/products/brain-tokyo-workshop
Language: Jupyter Notebook
License: Apache-2.0
License Family: permissive
Archived: true
Last push: 2024-07-09T17:49:39+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 2611, "days_push": 785, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1285, forks 335 (observed 2026-08-28T04:04:14.744233+00:00)

## What it is
A collection of research code releases from Google Brain's Tokyo team, including projects on weight agnostic neural networks, neuroevolution, attention-based agents, and evolution strategies with CLIP. It accompanies published papers with runnable implementations in Jupyter Notebook and Python.

## Use cases
- reproduce weight agnostic neural network research
- learn neuroevolution for reinforcement learning agents
- run attention-based self-interpretable agents on car racing environments
- fit concrete images with evolution strategies and CLIP
- study permutation-invariant neural networks for RL
- explore world models without forward prediction

## When to choose
- you want reference implementations of published Google Brain Tokyo research papers
- you are studying neuroevolution, evolution strategies, or attention-based RL agents
- you need a starting point for research extensions like CarRacing variants

## When to avoid
- you need a production-ready or maintained ML library with API stability
- you want a single cohesive framework rather than separate research codebases
- you need official Google support or long-term updates

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, reinforcement-learning, simulation
- domain: machine-learning, reinforcement-learning, artificial-intelligence, tutorials
- platform: python, cross-platform
- tags: research-code, neuroevolution, evolution-strategies, google-brain, neural-networks, jupyter-notebook

## Member repositories
- google/brain-tokyo-workshop (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:14.744233+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 2026-08-30T04:56:39.312627+00:00, confidence not recorded.
  - readme: https://github.com/google/brain-tokyo-workshop (fetched 2026-08-28T04:04:14.744233+00:00, sha aa4b6e5b887f)
- Data as of 2026-08-30T08:39:29.467469+00:00.