CytonRL: an Efficient Reinforcement Learning Open-source Toolkit Implemented in C++

Xiaolin Wang

CytonRL: an Efficient Reinforcement Learning Open-source Toolkit Implemented in C++

Machine Learning 2018-04-18 v1 Artificial Intelligence Machine Learning

Authors: Xiaolin Wang

Abstract

This paper presents an open-source enforcement learning toolkit named CytonRL (https://github.com/arthurxlw/cytonRL). The toolkit implements four recent advanced deep Q-learning algorithms from scratch using C++ and NVIDIA's GPU-accelerated libraries. The code is simple and elegant, owing to an open-source general-purpose neural network library named CytonLib. Benchmark shows that the toolkit achieves competitive performances on the popular Atari game of Breakout.

Keywords

compiler optimization software library

Cite

@article{arxiv.1804.05834,
  title  = {CytonRL: an Efficient Reinforcement Learning Open-source Toolkit Implemented in C++},
  author = {Xiaolin Wang},
  journal= {arXiv preprint arXiv:1804.05834},
  year   = {2018}
}

Related papers

View all related →

Computation and Language · Computer Science

CytonMT: an Efficient Neural Machine Translation Open-source Toolkit Implemented in C++