Sign inSign up

oceanthunder/principia

By oceanthunder

Updated 5 months ago

Playing Prince of Persia (1989) using Reinforcement Learning.

Image
Machine learning & AI
0

262

oceanthunder/principia repository overview

Principia: Experiments in POP using PPO.

GitHub: https://github.com/oceanthunder/Principia

How to run?

docker pull oceanthunder/principia 
xhost +local:docker
docker run --rm -it -e DISPLAY=$DISPLAY -v /tmp/.X11-unix:/tmp/.X11-unix --name principia --gpus all --ipc=host -p 6006:6006 oceanthunder/principia

after which run multippo.py to start the training [change the num_cpu param in multippo.py file to inc/dec the no. of environments in parallel]

CommandMode
python multippo.py 1Single Window (Only 1 GUI opens)
python multippo.py 2All Windows (GUI for every environment)
python multippo.py 3Headless (No windows, fastest)

Example:

python multippo.py 1

To access logs, open a new terminal and then:

docker exec -it principia /bin/bash

now, inside the container, type:

tensorboard --logdir logs --port 6006 --bind_all

Then, open up a browser and visit http://localhost:6006 to see tensorboard logs!

Tag summary

Content type

Image

Digest

sha256:f7f0b0981

Size

4.8 GB

Last updated

5 months ago

docker pull oceanthunder/principia