Mark
/
celeste-ai
Archived
1
0
Fork 0
Code Releases Activity

Updated README

master
Mark 2023-02-26 14:41:08 -08:00
parent 55a8a9d7cf
commit 938398f9b1
Signed by: Mark
GPG Key ID: AD62BB059C2AAEE4
1 changed files with 25 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

28
celeste/README.md
View File

@ -1,15 +1,37 @@
# Celeste-AI: A Celeste Classic DQL Agent
This is an attempt to create an agent that learns to play Celeste Classic.
This is an attempt to create a deep Q-learning agent that learns to play Celeste Classic.
## Contents
- `./resources`: contain files these scripts require. Notably, we have an (old) version of PICO-8 that's known to work with this script, and a version of Celeste Classic with telementery and delays called `hackcel.p8`.
- `./resources`: contains files this script requires. Notably, we have an (old) version of PICO-8 that's known to work with this script, and a version of Celeste Classic with telementery and delays called `hackcel.p8`.
- `ffmpeg.sh`: uses game screenshots to make real-time video of the agent's attempts. Read the script, it's pretty simple.
- `plot.py`: generates plots from model snapshots. These are placed in `model_data/current/plots/`.
## Setup
Before you set up Celeste-AI, you need to prepare PICO-8. See [`resources/README.md`](./resources/README.md)
This is designed to work on Linux. You will need `xdotool` to send keypresses to the game.
1. `cd` into this directory
2. Make and enter a venv
3. `pip install -e .`
3. `pip install -e .`
Once you're set up, you can...
- `python celeste_ai/train.py` to train a model
- `python plot.py` to make prediction plots
- `python test.py` to test a model
**Before running, be aware of the following:**
- Only one instance of PICO-8 can be running at a time. See `celeste.py`.
- `hackcel.p8` captures a screenshot of every frame. PICO-8 will probably place these on your desktop. Since this repo contains a rather old version of PICO-8, there is no way to change where it places screenshots. `train.py` will delete, move, and rename screenshots automatically during training, but you should tell it where your desktop is first.
- When you start training, a `model_data` directory will be created. It contains the following:
- `model_archive`: history of the model. Save interval is configured inside `train.py`
- `screenshots`: contains subdirectories. Each subdirectory contains the frames of one episode. Use `ffmpeg.sh` to turn these into a video.
- `plots`: generated by `plot.py`. Contains pretty plots.