https://github.com/niklasschmitz/deepqlearning
small experiments with agents learning atari games, implemented in jax/numpy
https://github.com/niklasschmitz/deepqlearning
deep-q-learning deep-reinforcement-learning jax
Last synced: 11 months ago
JSON representation
small experiments with agents learning atari games, implemented in jax/numpy
- Host: GitHub
- URL: https://github.com/niklasschmitz/deepqlearning
- Owner: niklasschmitz
- License: mit
- Created: 2019-01-28T18:04:41.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2019-03-16T14:10:58.000Z (over 7 years ago)
- Last Synced: 2025-07-13T22:36:01.389Z (about 1 year ago)
- Topics: deep-q-learning, deep-reinforcement-learning, jax
- Language: Python
- Size: 36.1 KB
- Stars: 7
- Watchers: 3
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# DeepQLearning
small experiments with agents learning atari games, implemented in jax/numpy
mostly following the 2013 NeurIPS paper [Playing Atari with Deep Reinforcement Learning
](https://arxiv.org/abs/1312.5602) by Mnih et al.
### Other Links
- experimental code setup partly based on this [pytorch implementation](https://github.com/philtabor/Youtube-Code-Repository/tree/master/ReinforcementLearning/DeepQLearning)
- nice explanation on the [preprocessing with frame skipping](https://danieltakeshi.github.io/2016/11/25/frame-skipping-and-preprocessing-for-deep-q-networks-on-atari-2600-games/)
This is a WIP