https://github.com/sash-a/hrlmujocoenvs.jl

HRL envs from Data efficient hierarchical reinforcement learning in Julia using Lyceum MuJoCo
https://github.com/sash-a/hrlmujocoenvs.jl

hierarchical-reinforcement-learning julialang reinforcement-learning-environments

Last synced: 4 months ago
JSON representation

HRL envs from Data efficient hierarchical reinforcement learning in Julia using Lyceum MuJoCo

• Host: GitHub
• URL: https://github.com/sash-a/hrlmujocoenvs.jl
• Owner: sash-a
• Created: 2021-09-01T14:05:51.000Z (almost 4 years ago)
• Default Branch: master
• Last Pushed: 2022-01-31T07:44:31.000Z (over 3 years ago)
• Last Synced: 2025-01-18T03:25:13.992Z (5 months ago)
• Topics: hierarchical-reinforcement-learning, julialang, reinforcement-learning-environments
• Language: Julia
• Homepage:
• Size: 1.81 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

        
# HrlMuJoCoEnvs.jl

HRL envs from [Data efficient hierarchical reinforcement learning](https://arxiv.org/abs/1805.08296) in Julia using [Lyceum MuJoCo](https://github.com/Lyceum/LyceumMuJoCo.jl)

## Available environments

* Ant gather

* Point gather

* Ant maze

* Point maze

* Ant push

* Ant fall

## Installation

Make sure you check the install instructions for [Lyceum MuJoCo](https://github.com/Lyceum/LyceumMuJoCo.jl)

```

pkg> add https://github.com/sash-a/HrlMuJoCoEnvs.jl/

```

## Example usage

```

using HrlMuJoCoEnvs

using LyceumMuJoCo

env = HrlMuJoCoEnvs.AntGatherEnv()

for i in 1:100

    step!(env)

    o = getobs(env)

    setaction!(env, rand(8))

    @show getreward(env)

    if isdone(env)

        println("done")

    end

end

```

## Examples of the environments

### Ant Gather

![](vids/antgather.gif)

### Ant Maze

![](vids/antmaze.gif)

### Ant Push

![](vids/antpush.gif)

### Ant Fall

![](vids/antfall.gif)

ps. appologies for some poor coding practise, this is research code.