CytonRL: an Efficient Reinforcement Learning Open-source Toolkit Implemented in C++
National Institute of Information and Communications Technology, Japan
arXiv:1804.05834 [cs.LG], (14 Apr 2018)
This paper presents an open-source enforcement learning toolkit named 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.
April 22, 2018 by hgpu
