Xuntian's repositories
Meta-Learning-for-StarCraft-II-Minigames
We reproduced DeepMind's results and implement a meta-learning (MLSH) agent which can generalize across minigames.
wechat_jump_game
python 微信《跳一跳》辅助
universe-starter-agent
A starter agent that can solve a number of universe environments.
universe
Universe: a software platform for measuring and training an AI's general intelligence across the world's supply of games, websites and other applications.
Top-RL-Algorithem-List-FeUdal-networks-
Top Vision Github Projects
sac
Soft Actor-Critic
AStream
A DASH segment size aware rate adaptation model for DASH
TPAMI_2018_DHP
DHP paper in submission for TPAMI.
GTN
This repo provides code for all the results reported in GTN paper.
pytorch-a2c-ppo-acktr
PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO) and Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR).
pytorch-kinds-of-GAN-collections
Collection of generative models in Pytorch version.
maml
Code for "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"
tf-rnn-attention
Tensorflow implementation of attention mechanism for text classification tasks.
feudal_networks
An implementation of FeUdal Networks for Hierarchical Reinforcement Learning as published : https://arxiv.org/abs/1703.01161
Chinese-chess-with-Deep-Reinforcement-Learning
Chinese chess with Deep Reinforcement Learning in cpp and python, to be completed. I have a problem with cpp-python-tf communication now.
MLSH-Ubuntu
MLSH Code with small changes to run in Ubuntu
QA
使用深度学习算法实现的中文问答系统
lstm_ATTENTION_tf
Add attention layer to LSTM/word2vec model for sentiment analysis using tensorflow
sequence_tagging
Named Entity Recognition (LSTM + CRF) - Tensorflow
papers_about_gan
This repo offers some papers to read on GANs.
rtl8812AU
Linux driver for Realtek 802.11ac based on Realtek's 5.1.5 version
ResNeXt-DenseNet
Pytorch Implementation for ResNet, Pre-Activation ResNet, ResNeXt and DenseNet
NER-LSTM-CRF_details-in-Chinese
An easy-to-use named entity recognition (NER) toolkit, implemented the Bi-LSTM+CRF model in tensorflow.
maml_rl
Code for RL experiments in "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"
Meta-Learning-List-FeUdal-networks-
Meta Reinforcement Learning Experiments