General Purpose Python Library
Project description
joatmon (jack of all trades, master of none)
What is included?
As of today, the following algorithms have been implemented:
As of today, the following environments have been implemented:
- Rubick's Cube
- 2048 Puzzle
- Sokoban
- Game of 15
- Chess
As of today, the following networks have been implemented:
You can find more information in the doc.
Installation
- Install joatmon from Pypi (recommended):
pip install joatmon
Install from Github source:
git clone https://github.com/malkoch/joatmon.git
cd joatmon
python setup.py install
Examples
If you want to run the examples, you'll also have to install:
- gym by OpenAI: Installation instruction
Once you have installed everything, you can try out a simple example:
python examples/sokoban_dqn.py
python examples/sokoban_ddpg.py
How to run the tests
To run the tests locally, you'll first have to install the following dependencies:
pip install pytest pytest-xdist pep8 pytest-pep8 pytest-cov python-coveralls
You can then run all tests using this command:
py.test tests/.
If you want to check if the files conform to the PEP8 style guidelines, run the following command:
py.test --pep8
If you want to check the code coverage, run the following command:
py.test --cov=joatmon tests/
References
- Mnih, Volodymyr, et al. "Playing atari with deep reinforcement learning." arXiv preprint arXiv:1312.5602 (2013).
- Lillicrap, Timothy P., et al. "Continuous control with deep reinforcement learning." arXiv preprint arXiv: 1509.02971 (2015).
- Fujimoto, Scott, Herke van Hoof, and David Meger. "Addressing function approximation error in actor-critic methods." arXiv preprint arXiv:1802.09477 (2018).
- Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet classification with deep convolutional neural networks." Advances in neural information processing systems. 2012.
- Goodfellow, Ian, et al. "Generative adversarial nets." Advances in neural information processing systems. 2014.
- Mirza, Mehdi, and Simon Osindero. "Conditional generative adversarial nets." arXiv preprint arXiv:1411.1784 (2014).
- Karras, Tero, et al. "Progressive growing of gans for improved quality, stability, and variation." arXiv preprint arXiv:1710.10196 (2017).
- He, Kaiming, et al. "Deep residual learning for image recognition." Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.
- Ronneberger, Olaf, Philipp Fischer, and Thomas Brox. "U-net: Convolutional networks for biomedical image segmentation." International Conference on Medical image computing and computer-assisted intervention. Springer, Cham, 2015.
- Simonyan, Karen, and Andrew Zisserman. "Very deep convolutional networks for large-scale image recognition." arXiv preprint arXiv:1409.1556 (2014).
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.