# araffin/rl-baselines-zoo

A collection of 100+ pre-trained RL agents using Stable Baselines, training and hyperparameter optimization included.

Repository: https://github.com/araffin/rl-baselines-zoo
Canonical: https://ross.abutalabs.com/products/rl-baselines-zoo
Homepage: https://stable-baselines.readthedocs.io/
Language: Python
License: MIT
License Family: permissive
Topics: rl, zoo, reinforcement-learning, stable-baselines, openai-gym, openai, gym, pybullet, hyperparameters, optimization, hyperparameter-optimization, hyperparameter-search, hyperparameter-tuning
Archived: true
Last push: 2022-10-17T13:48:30+00:00

## Health v2 (maintenance only)
Score: 10/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2863, "days_push": 1416, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: archived
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1203, forks 210 (observed 2026-08-28T04:03:58.598076+00:00)

## What it is
A collection of 100+ pre-trained reinforcement learning agents built with Stable Baselines, including tuned hyperparameters for each environment and scripts for training, evaluation, and hyperparameter optimization with Optuna. This repository is no longer maintained; its successor is RL-Baselines3 Zoo.

## Use cases
- run pre-trained RL agents on gym environments
- benchmark reinforcement learning algorithms
- find tuned hyperparameters for RL training
- train RL agents with sensible defaults
- tune RL hyperparameters with Optuna
- watch trained agents play Atari or PyBullet environments

## When to choose
- you want ready-made trained RL agents for OpenAI Gym or PyBullet environments
- you need baseline hyperparameters for RL algorithm comparisons
- you want a simple CLI to train and evaluate Stable Baselines agents

## When to avoid
- you are starting a new project - use the maintained RL-Baselines3 Zoo instead
- you need Stable-Baselines3 or PyTorch-based agents
- you require ongoing support or updates

## Facets
- artifact type: dataset
- maturity: abandoned
- function: reinforcement-learning, benchmarking, machine-learning
- domain: reinforcement-learning, machine-learning, gaming-tools
- platform: python, windows
- tags: pretrained-agents, stable-baselines, openai-gym, pybullet, hyperparameter-tuning, optuna, rl-zoo, linux, macos

## Member repositories
- araffin/rl-baselines-zoo (main) score 10

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:58.598076+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 2026-08-30T06:19:44.299369+00:00, confidence not recorded.
  - readme: https://github.com/araffin/rl-baselines-zoo (fetched 2026-08-28T04:03:58.598076+00:00, sha 97784116c4b3)
- Data as of 2026-08-30T08:39:29.467469+00:00.