45 
45%
deep-rts
· GitHub
per-arne neural-networks reinforcement-learning deep-learning game deep-reinforcement-learning python tree-search artificial-intelligence cpp ai
A Real-Time-Strategy game for Deep Learning research
Repository Stats
221 stars
37 forks
Repository Activity
This repository has been starred 221 times and forked 37 times, showing its popularity in the developer community.
README Preview
<img src ="./docs/logo.png" width="50%" height="50%"/> ## Description [](https://travis-ci.org/cair/deep-rts) [](https://cair.github.io/deep-rts) [](https://raw.githubusercontent.com/cair/DeepRTS/c%2B%2B/LICENCE.MIT) DeepRTS is a high-performance Real-TIme strategy game for Reinforcement Learning research. It is written in C++ for performance, but provides an python interface to better interface with machine-learning toolkits. Deep RTS can process the game with over **6 000 000** steps per second and **2 000 000** steps when rendering graphics. In comparison to other solutions, such as StarCraft, this is over **15 000% faster simulation** time running on Intel i7-8700k with Nvidia RTX 2080 TI. The aim of Deep RTS is to bring a more affordable and sustainable solution to RTS AI re
