Hongzi Mao

Tensorflow implementation of Asynchronous Advantage Actor Critic (A3C) from "Asynchronous Methods for Deep Reinforcement Learning".

hongzimao

Learning Scheduling Algorithms for Data Processing Clusters

hongzimao

Resource Management with Deep Reinforcement Learning (HotNets '16)

hongzimao

Variance Reduction for Reinforcement Learning in Input-Driven Environments (ICLR '19)

hongzimao

Neural Adaptive Video Streaming with Pensieve (SIGCOMM '17)

hongzimao