Pinned Repositories
abbrv.jabref.org
A repository of abbreviations for references, e.g., for conferences, journals, institutes, etc.
CS-Notes
:books: 技术面试必备基础知识、Leetcode、计算机操作系统、计算机网络、系统设计、Java、Python、C++
Full-Duplex-User-Pairing
This project is about user pairing in a full-duplex communication system based on the deep reinforcement learning (DQN). We use 32 different groups of users to train the agent, each group include 6 uplink users and 8 downlink users. First, we transform the problem of user pairing to the markov decision process. Then, to accelerate the training speed, we added some expert experience to the replay buffer to make the agent learn quikly.
Full-Duplex-User-Pairing_1
This project is about user pairing in a full-duplex communication system based on the deep reinforcement learning (DQN). We use 32 different groups of users to train the agent, each group include 6 uplink users and 8 downlink users. First, we transform the problem of user pairing to the markov decision process. Then, to accelerate the training speed, we added some expert experience to the replay buffer to make the agent learn quikly.
Machine-Learning
:zap:机器学习实战（Python3）：kNN、决策树、贝叶斯、逻辑回归、SVM、线性回归、树回归
Reinforcement-learning-with-tensorflow
Simple Reinforcement learning tutorials
ZJU-nCov-Hitcarder-Sample
Sample of https://github.com/Long0x0/ZJU-nCov-Hitcarder.
TianLiang96's Repositories
TianLiang96/Full-Duplex-User-Pairing_1
This project is about user pairing in a full-duplex communication system based on the deep reinforcement learning (DQN). We use 32 different groups of users to train the agent, each group include 6 uplink users and 8 downlink users. First, we transform the problem of user pairing to the markov decision process. Then, to accelerate the training speed, we added some expert experience to the replay buffer to make the agent learn quikly.
TianLiang96/Reinforcement-learning-with-tensorflow
Simple Reinforcement learning tutorials
TianLiang96/abbrv.jabref.org
A repository of abbreviations for references, e.g., for conferences, journals, institutes, etc.
TianLiang96/CS-Notes
:books: 技术面试必备基础知识、Leetcode、计算机操作系统、计算机网络、系统设计、Java、Python、C++
TianLiang96/Full-Duplex-User-Pairing
This project is about user pairing in a full-duplex communication system based on the deep reinforcement learning (DQN). We use 32 different groups of users to train the agent, each group include 6 uplink users and 8 downlink users. First, we transform the problem of user pairing to the markov decision process. Then, to accelerate the training speed, we added some expert experience to the replay buffer to make the agent learn quikly.
TianLiang96/Machine-Learning
:zap:机器学习实战（Python3）：kNN、决策树、贝叶斯、逻辑回归、SVM、线性回归、树回归
TianLiang96/ZJU-nCov-Hitcarder-Sample
Sample of https://github.com/Long0x0/ZJU-nCov-Hitcarder.