![](/assets/poke_map.gif?raw=true)
Experiments training reinforcement learning agents to play Pokemon Red. Watch the Video on Youtube!
![](/assets/Pokemon YT5 FFFFinal.jpg?raw=true)
- 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 beea9bcae617fdf159b045185467ae58b2e4a48b9a
, which you can verify by runningshasum PokemonRed.gb
. - Move into the
baselines/
directory:
cd baselines
- Install dependencies:
pip install -r requirements.txt
It may be necessary in some cases to separately install the SDL libraries. - 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 that 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.
Note: By default this can use up to ~100G of RAM. You can decrease this by reducing the num_cpu
or ep_length
, but it may affect the results. Also, the model behavior may become degenerate for up to the first 50 training iterations or so before starting to improve. This could likely be fixed with better hyperparameters but I haven't had the time or resources to sweep these.
- Previous steps 1-3
- Run:
python run_baseline_parallel.py
You can view the current state of each emulator, plot basic stats, and compare to previous runs using the VisualizeProgress.ipynb
notebook.
Map visualization code can be found in visualization/
directory.