Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/PWhiddy/PokemonRedExperiments
Playing Pokemon Red with Reinforcement Learning
https://github.com/PWhiddy/PokemonRedExperiments
Last synced: 2 months ago
JSON representation
Playing Pokemon Red with Reinforcement Learning
- Host: GitHub
- URL: https://github.com/PWhiddy/PokemonRedExperiments
- Owner: PWhiddy
- License: mit
- Created: 2019-12-25T07:52:16.000Z (about 5 years ago)
- Default Branch: master
- Last Pushed: 2024-10-23T01:06:42.000Z (3 months ago)
- Last Synced: 2024-10-29T15:03:49.843Z (2 months ago)
- Language: Jupyter Notebook
- Homepage:
- Size: 66.1 MB
- Stars: 6,916
- Watchers: 72
- Forks: 634
- Open Issues: 68
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- awesome-rainmana - PWhiddy/PokemonRedExperiments - Playing Pokemon Red with Reinforcement Learning (Jupyter Notebook)
- AiTreasureBox - PWhiddy/PokemonRedExperiments - 01-07_7072_-1](https://img.shields.io/github/stars/PWhiddy/PokemonRedExperiments.svg)|Playing Pokemon Red with Reinforcement Learning| (Repos)
- awesome-pokemon - PokemonRedExperiments - Playing Pokémon Red with Reinforcement Learning. (Development Projects)
README
# Train RL agents to play Pokemon Red
### New 1-29-24! - [Multiplayer Live Training Broadcast](https://github.com/pwhiddy/pokerl-map-viz/) 🎦 🔴 [View Here](https://pwhiddy.github.io/pokerl-map-viz/)
Stream your training session to a shared global game map using the [Broadcast Wrapper](/baselines/stream_agent_wrapper.py)
See how in [Training Broadcast](#training-broadcast) section
## Watch the Video on Youtube!
## Join the discord server
[](http://discord.gg/RvadteZk4G)
## Running the Pretrained Model Interactively 🎮
🐍 Python 3.10+ is recommended. Other versions may work but have not been tested.
You also need to install ffmpeg and have it available in the command line.
### Windows Setup
Refer to this [Windows Setup Guide](windows-setup-guide.md)
### For AMD GPUs
Follow this [guide to install pytorch with ROCm support](https://rocm.docs.amd.com/projects/radeon/en/latest/docs/install/wsl/howto_wsl.html)
### Linux / MacOS
1. Copy your legally obtained Pokemon Red ROM into the base directory. You can find this using google, it should be 1MB. Rename it to `PokemonRed.gb` if it is not already. The sha1 sum should be `ea9bcae617fdf159b045185467ae58b2e4a48b9a`, which you can verify by running `shasum PokemonRed.gb`.
2. Move into the `baselines/` directory:
```cd baselines```
3. Install dependencies:
```pip install -r requirements.txt```
It may be necessary in some cases to separately install the SDL libraries.
4. Run:
```python run_pretrained_interactive.py```
Interact with the emulator using the arrow keys and the `a` and `s` keys (A and B buttons).
You can pause the AI's input during the game by editing `agent_enabled.txt`
Note: the Pokemon.gb file MUST be in the main directory and your current directory MUST be the `baselines/` directory in order for this to work.
## Training the Model 🏋️
### 10-21-23: Updated Version!
This version still needs some tuning, but it can clear the first gym in a small fraction of the time and compute resources. It can work with as few as 16 cores and ~20G of RAM. This is the place for active development and updates!
1. Previous steps 1-3
2. Run:
```python run_baseline_parallel_fast.py```
### V2
Replaces the frame KNN with a coordinate based exploration reward, as well as some other tweaks. Beats the gym more reliably and sometimes is able to get to Cerulean!
1. Previous steps
2. Run:
```python baseline_fast_v2.py```
## Tracking Training Progress 📈
### Training Broadcast
Stream your training session to a shared global game map using the [Broadcast Wrapper](/baselines/stream_agent_wrapper.py) on your environment like this:
```python
env = StreamWrapper(
env,
stream_metadata = { # All of this is part is optional
"user": "super-cool-user", # choose your own username
"env_id": id, # environment identifier
"color": "#0033ff", # choose your color :)
"extra": "", # any extra text you put here will be displayed
}
)
```
Hack on the broadcast viewing client or set up your own local stream with this repo:
https://github.com/pwhiddy/pokerl-map-viz/
### Local Metrics
The current state of each game is rendered to images in the session directory.
You can track the progress in tensorboard by moving into the session directory and running:
```tensorboard --logdir .```
You can then navigate to `localhost:6006` in your browser to view metrics.
To enable wandb integration, change `use_wandb_logging` in the training script to `True`.
## Static Visualization 🐜
Map visualization code can be found in `visualization/` directory.
## Supporting Libraries
Check out these awesome projects!
### [PyBoy](https://github.com/Baekalfen/PyBoy)
### [Stable Baselines 3](https://github.com/DLR-RM/stable-baselines3)
