deeprl
deeprl copied to clipboard
Universal library for deep reinforcement learning.
Deep Reinforcement Learning
Quick Start
TODO
Available algorithms
Algorithm | Repository | Example json | Documentation |
---|---|---|---|
Discrete DeepQ | deeprl | TODO | TODO |
Asynchronous DeepQ (soon) | deeprl | TODO | TODO |
Available Simulators
Algorithm | Repository | Example json | Documentation |
---|---|---|---|
Karpathy Game | SimulatorZoo | TODO | TODO |
Requirements
-
tensorflow == 0.7
for Automated Differentiation. - SimulatorZoo for the models
Documentation
- Quick start guide.
- Writing your own simulator.
- Adopting Existing Algorithm to different type of input.
- Contributing to this repository.
Contributors
- stas-sl (found critical bug in Discrete Deepq)
Mentions
- NIPS
- https://twitter.com/pythontrending/status/665928320245198848
- http://www.slideshare.net/tw_dsconf/tensorflow-tutorial
- http://esbuzz.net/trends/watch/vid88Y773WD3kkh4