Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/louis030195/xmoto-gym
OpenAi's gym environment for Xmoto game - reinforcement learning research
https://github.com/louis030195/xmoto-gym
artificial-intelligence deep-learning deep-neural-networks deeplearning machine-learning machinelearning python reinforcement-learning
Last synced: 12 days ago
JSON representation
OpenAi's gym environment for Xmoto game - reinforcement learning research
- Host: GitHub
- URL: https://github.com/louis030195/xmoto-gym
- Owner: louis030195
- Created: 2018-06-20T19:48:58.000Z (over 6 years ago)
- Default Branch: master
- Last Pushed: 2019-06-08T16:17:55.000Z (over 5 years ago)
- Last Synced: 2024-12-20T12:12:25.642Z (17 days ago)
- Topics: artificial-intelligence, deep-learning, deep-neural-networks, deeplearning, machine-learning, machinelearning, python, reinforcement-learning
- Language: Jupyter Notebook
- Homepage:
- Size: 156 MB
- Stars: 2
- Watchers: 4
- Forks: 0
- Open Issues: 6
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Xmoto AI
OpenAi Gym with Xmoto !
# Actions
- W = ADVANCE
- A = LIFT FRONT WHEEL
- S = BRAKE
- D = LIFT BACK WHEEL
- SPACE = change direction
- NA = no action
# Observations
- Screen pixels (200, 150, 3)
# Installation
```
pip install gym_xmoto
sudo apt-get install faketime
sudo apt-get install xmoto
```
# Usage
Example
```
python example.py
```
For more details check [this](https://github.com/louis030195/xmoto_learning)
## Docker
(Currently doesn't work Seg fault at example in run)
```
docker build .
docker run -p 5900:5900
vncviewer localhost:5900
```
**Second agent:**
```
docker run -p 5901:5900
vncviewer localhost:5901
```
...
## Roadmap
- [ ] More observations from Xmoto API
- [ ] Better score detection performance
- [ ] Synchronisation algorithm - faketime
- [ ] Distributed training
- [x] Reward on hit apple (decrease score)