Top AI Repos — open-source AI, indexed and scored
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
Top AI Repos tracks AI repositories on GitHub and answers two different questions about each one: is it moving right now, and would you bet a product on it.
A repository of high-performing hierarchical reinforcement learning models and algorithms.
| Date | Stars |
|---|---|
| 2026-07-31 | 339 |
| 2026-08-02 | 339 |
| 2026-08-03 | 339 |
| 2026-08-06 | 339 |
Today
— stars today
This week
— stars this week
This month
— stars this month
Momentum
0.0
growth rate 0.00%/day
[](https://github.com/AboudyKreidieh/h-baselines/actions/workflows/ci.yml)
[](https://coveralls.io/github/AboudyKreidieh/h-baselines?branch=master)
[](https://github.com/AboudyKreidieh/h-baselines/blob/master/LICENSE)
# h-baselines
`h-baselines` is a repository of high-performing and benchmarked
hierarchical reinforcement learning models and algorithms. This repository is
motivated by, and partially adapted from, the
[baselines](https://github.com/openai/baselines) and
[stable-baselines](https://github.com/hill-a/stable-baselines) repositories.
You can learn more about the supported models and algorithms within this
repository by reviewing this README.
## Contents
1. [Setup Instructions](#1-setup-instructions)
1.1. [Basic Installation](#11-basic-installation)
1.2. [Installing MuJoCo](#12-installing-mujoco)
1.3. [Importing AntGather](#13-importing-antgather)
1.4. [Installing Flow](#14-installing-flow)
2. [Supported Models/Algorithms](#2-supported-modelsalgorithms)
2.1. [RL Algorithms](#21-rl-algorithms)
2.1.1. [Synchronous Updates](#211-synchronous-updates)
2.2. [Fully Connected Neural Networks](#22-fully-connected-neural-networks)
2.3. [Goal-Conditioned HRL](#23-goal-conditioned-hrl)
2.3.1. [Meta Period](#231-meta-period)
2.3.2. [Intrinsic Rewards](#232-intrinsic-rewards)
2.3.3. [HIRO (Data Efficient Hierarchical Reinforcement Learning)](#233-hiro-data-efficient-hierarchical-reinforcement-learning)
2.3.4. [HAC (Learning Multi-level Hierarchies With Hindsight)](#234-hac-learning-multi-level-hierarchies-with-hindsight)
2.3.5. [CHER (Inter-Level Cooperation in Hierarchical Reinforcement Learning)](#235-cher-inter-level-cooperation-in-hierarchical-reinforcement-learning)
2.4. [Multi-Agent Policies](#24-multi-agent-policies)
3. [Environments](#3-environments)
3.1. [MuJoCo Environments](#31-mujoco-environments)
3.2. [Flow Environments](#32-flow-environments)
4. [Citing](#4-citing)
5. [Bibliography](#5-bibliography)
# 1. Setup Instructions
## 1.1 Basic Installation
To install the h-baselines repository, begin by opening a terminal and set the
working directory of the terminal to match
```shell script
cd path/to/h-baselines
```
Next, create and activate a conda environment for this repository by running
the commands in the script below. Note that this is not required, but highly
recommended. If you do not have Anaconda on your device, refer to the provided
links to install either [Anaconda](https://www.anaconda.com/download) or
[Miniconda](https://conda.io/miniconda.html).
```shell script
conda env create -f environment.yml
source activate h-baselines
```
Finally, install the contents of the repository onto your conda environment (or
your local python build) by running the following command:
```shell script
pip install -e .
```
If you would like to (optionally) validate that the repository was successfully
installed and is running, you can do so by executing the unit tests as follows:
```shell script
nose2
```
The test should return a message along the lines of:
----------------------------------------------------------------------
Ran XXX tests in YYYs
OK
## 1.2 Installing MuJoCo
In order to run the MuJoCo environments described within the README, you
will need to install MuJoCo and the mujoco-py package. To install both
components follow the setup instructions located
[here](https://github.com/openai/mujoco-py). This package should work
with all Excerpt of 47,464 characters
Read on GitHubWould you bet a product on this? Bounded 0–100 and slow moving.
matched fp:ab61f715f972ead1, llm:description: 'A repository of high-performing hierarchical reinforcement learning models and algorithms.'