gaobingaobingaobin,github

-rl-double_dueling_dqn

This repository implements the 'double dueling DQN', which extends the DQN.

-rl-my_ieee_journal_imple.-ddpg-

This repository contains my work submitted to IEEE Transactions on Vehicular Technology (TVT). The journal is about 'proactive caching policy learning in mmWave vehicular networks' with DDPG. Some part of the contents will be uploaded after submission.

1bit_precoding_vlsi

Simulation code for the C1PO and C2PO precoder algorithms in 1-bit massive MIMO systems

3d_pose_estimation_cvpr2016

3ddescriptornet

Learning Descriptor Networks for 3D Shape Synthesis and Analysis

5gm-beam-selection

Beam-selection for mmWave MIMO using machine learning

5gm-data

Datasets and code for machine learning in 5G mmWave MIMO systems involving mobility (5GMdata)

5gm-rwi-simulation

5GMdata project: Scripts to repeatedly invoke Remcom Wireless Insite and SUMO

60ghz_multicast

Scalable Directional Multicast Protocol for 60 GHz (millimeter wave communication) Wireless LANs

aaai16

aaai17

aaai18-code

The code of AAAI18 paper "Learning Structured Representation for Text Classification via Reinforcement Learning".

aaai2016

Discriminative Analysis Dictionary Learning

aaai_submission_3487

AAAI Submission Poster 3487

acc-2015

Code to generate figures from the paper "Optimal experiment design for physiological parameter estimation using hyperpolarized carbon-13 magnetic resonance spectroscopy" by John Maidens, Peder E. Z. Larson and Murat Arcak

acc-2016

Code to generate figures from the paper "Semidefinite relaxations in optimal experiment design with application to substrate injection for hyperpolarized MRI" by John Maidens and Murat Arcak