shaoyn0817
Follow
Stars
Paper list for constrained policy optimization in reinforcement learning.
The repository archives papers regarding the combination of combinatorial optimization and machine learning and corresponding reading notes.
An implementation of Policy Gradients Using Gaussian Distributed Actions for solving the ContinuousMountainCar-v0 problem using NumPy
Temporal-difference learning is a method to compute the values of all states by sampling the environment. It approximates the current estimate of a state value based on previously learned estimates…
tensorflow实战练习，包括强化学习、推荐系统、nlp等
Libraries for connecting to the BitMEX API.
OKEX is popular in some of the Asian countries. But the official documentation is incomplete, example of sample is not usable. This is a tested working websocket API connection for OKEX.
955 不加班的公司名单 - 工作 955，work–life balance (工作与生活的平衡)
Repo for counting stars and contributing. Press F to pay respect to glorious developers.
CTR prediction models based on deep learning(基于深度学习的广告推荐CTR预估模型)
Must-read papers on network representation learning (NRL) / network embedding (NE)
Reinforcement Learning for Relation Classification from Noisy Data(TensorFlow)
An Efficient Enterprise-class Container Engine
基于seq2seq模型的简单对话系统的tf实现，具有embedding、attention、beam_search等功能，数据集是Cornell Movie Dialogs
Reinforcement Learning for Relation Classification from Noisy Data(AAAI2018)
Sentiment analysis-Dataset：25000 IMDB Comments（En）With Keras based on Tensorflow
My personal Java NLP toolkit that serves as an interface to various existing NLP libraries.