super-mario-neat - GitLite

KO | EN

gitlite — search

#javascript #hacktoberfest #react #llm #machine-learning #deep-learning #linux #nodejs #cli #vue #security #ios #mcp #open-source

super-mario-neat

(★ 105)

This program evolves an AI using the NEAT algorithm to play Super Mario Bros.

파일 탐색기

최종 버전 다운로드 (.zip)

- - site.css
  - style.css
- - ad_status.js
  - analytics.js
  - angular-animate.min.js
  - angular-resource.min.js
  - angular-touch.min.js
  - angular.min.js
  - base.js
  - bodymovin.js
  - BvTIEteILZqRcskLLoLlPBoiUTY3LsR-M3DKm3lfPek.js
  - glue-detect.min.js
  - glue-lite.min.js
  - gtm.js
  - hercules.min.js
  - hNDkjy2rXG4.html
  - photo.jpg
  - remote.js
  - ScrollToPlugin.min.js
  - site.min.js
  - TweenMax.min.js
  - world1-1.gif
  - www-embed-player.js
  - www-player-2x-webp-vflPhQGXh.css
- .DS_Store
- index.html
- mario.tex
- avg_fitness.svg
- Digraph.gv
- Digraph.gv.svg
- mario.pdf
- speciation.svg
- world1-1.gif
- world1-1.mp4
- - gen_2284
  - neat-checkpoint-2492
- config
- cont_train.py
- finisher.pkl
- main.py
- run.py
- train.py
- visualize.py
.gitattributes
.gitignore
LICENSE.md
README.md
requirements.txt

# 설치 가이드

1. 코드 내려받기

git clone https://github.com/vivek3141/super-mario-neat

깃허브에서 프로젝트 코드 전체를 내 컴퓨터로 내려받습니다.

cd super-mario-neat

방금 내려받은 프로젝트 폴더 안으로 이동합니다.

2. Python

쉬움 추천

사전 준비물

Git GitHub에서 프로젝트 코드를 내려받으려면 필요합니다.
Python 3 설치 시 'Add Python to PATH' 옵션을 꼭 체크하세요 (Windows).

pip install -r requirements.txt

requirements.txt 등에 명시된 파이썬 라이브러리를 설치합니다.

python <실행할 파일명>.py # README에서 정확한 실행 파일명을 확인하세요

파이썬 스크립트(또는 모듈)를 실행합니다.

✅ 에러 메시지 없이 실행되고 터미널에 안내 문구가 출력되면 정상입니다.

// repository documentation

Was this content helpful?

★ 0 (0 ratings)

# Super Mario NEAT
This program uses the NEAT algorithm to evolve a 
Neural Network to play the original Super Mario Bros.
<br>

## Requirements
You can install the requirements by running <br >
```bash 
sudo apt install fceux
python3 -m pip install -r requirements.txt
```

Or if on windows, run
```bash
python3 -m pip install -r requirements.txt
```
* Make sure you have FCEUX downloaded and added to PATH

## Training
The finisher.pkl file contains the best genome on generation 2284.
In ./Files, you can find the backup for generation 2284, and the backup for generation 2492,
which is where I stopped training. <br />
<br>
You can continue training by running <br>
```bash
python3 main.py cont_train --gen <num_generations> --file <file>
```
<br>

## Running
To run the finisher.pkl file, run
<br>
```bash
python3 main.py run
```

or run <br>
```bash
python3 run.py
```
If you want to run a different file, run<br>
```bash
python3 main.py run --file <file_name>
```
<br>

## Config
For debugging values, you can change any of the values in the config file. Note that you have to train from the 1st generation for some to take effect.
<br>
To use a different config file when training, specify `--config <config file>` when running `main.py`.
<br>
## Multiprocessing
This program uses the build in python module multiprocessing, which is used for parallel computing. You can adjust the amount of genomes
to run at once by specifying `--parallel <num_of_genomes>` when running `main.py`.
<br>
## Levels
The default level is World 1, Level 1. This can be changed by specifying `--level <level>` when running `main.py`. For example, <br>
`python3 main.py train --gen 100 --level "1-1"` will use 1-1.
<br>
## Result
The `finisher.pkl` file is trained to complete 1-1. It can complete it around 50% of the time. The `run.py` file keeps running the
simulation until it completes the level. `Ctrl + C` will stop it.
<br>
<br>
<img src="https://github.com/vivek3141/super-mario-neat/raw/master/img/world1-1.gif">
<br>

## Additional Information
The [Wiki](https://github.com/vivek3141/super-mario-neat/wiki) contains more information regarding the specifics of implementing certain parts.