https://github.com/embersarc/gym-rocketlander

A SpaceX Rocket Lander environment for OpenAI gym using Box2D
https://github.com/embersarc/gym-rocketlander

Last synced: about 1 month ago
JSON representation

A SpaceX Rocket Lander environment for OpenAI gym using Box2D

• Host: GitHub
• URL: https://github.com/embersarc/gym-rocketlander
• Owner: EmbersArc
• License: mit
• Created: 2017-08-03T19:29:06.000Z (almost 8 years ago)
• Default Branch: master
• Last Pushed: 2021-01-19T18:39:05.000Z (over 4 years ago)
• Last Synced: 2025-04-02T21:11:52.764Z (about 2 months ago)
• Language: Python
• Homepage:
• Size: 7.81 KB
• Stars: 299
• Watchers: 14
• Forks: 44
• Open Issues: 1
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# ![GIF](https://thumbs.gfycat.com/CoarseEmbellishedIsopod-max-14mb.gif)

[Click here for higher quality video](https://gfycat.com/CoarseEmbellishedIsopod)

The objective of this environment is to land a rocket on a ship. The environment is highly customizable and takes discrete or continuous inputs.

### Installation

```

cd gym-rocketlander

pip install -e .

```

### Usage

Once the has been installed, it can be used like any other Gym environment:

```py

env = gym.make("gym_rocketlander:rocketlander-v0")

```

### STATE VARIABLES  

The state consists of the following variables:

  * x position  

  * y position  

  * angle  

  * first leg ground contact indicator  

  * second leg ground contact indicator  

  * throttle  

  * engine gimbal  

  

If VEL_STATE is set to true, the velocities are included:  

  * x velocity  

  * y velocity  

  * angular velocity  

  

### CONTROL INPUTS  

Discrete control inputs are:  

  * gimbal left  

  * gimbal right  

  * throttle up  

  * throttle down  

  * use first control thruster  

  * use second control thruster  

  * no action  

    

Continuous control inputs are:  

  * gimbal (left/right)  

  * throttle (up/down)  

  * control thruster (left/right)