📖 作为对《C++ Concurrency in Action》英文版的中文翻译。

A implement of Clustering by fast search and find of density peaksd

reinfore learning tool box, contains trpo, a3c algorithm for continous action space

📚 Freely available programming books

Applying the deep learning techniques from Alpha Go to play tic-tac-toe

trust region policy optimization base on gym and tensorflow, can run in distribution mode

This is an implementation sketch of the KinectFusion system described by Newcombe et al.

dataset and code for 2016 paper "Learning a Driving Simulator"