Leepand's repositories
MLOps-practice
MLops—实践机器学习从开发到生产
mini-mlops
MLOps for (online) machine/reinforcement learning
py_functions
python 函数集、工具
AlgoLink-docs
AlgoLink说明手册
bandit-recom
通过AI驱动的推荐,提高客户满意度和消费。适用于您的主页、产品详情、电子邮件营销活动等。
domino-research
Projects developed by Domino's R&D team
ebonite
machine learning lifecycle framework
featurekit
feature tools
GradX-AI
我们的AI个性化以RL为基础的,旨在将游戏从“一刀切”的模式转变为根据个别玩家喜好定制体验的模式。为了实现这一目标,我们创建了GradX-AI系统,这是一个开创性的实时推荐系统。
leepand
RLXtreme是一个轻量级且高效的Python强化学习算法包,旨在提供极致性能和灵活业务应用的强化学习解决方案。
leepand.github.io
javascript demo of MWUA(Multiplicative Weights Update Algorithm)
LightFM-Dataset-Helper
python package to help preparing Dataframes (csv ... ) for LightFM module for easy Training
LinkToFeatuteStore
LinkTOFeatuteStore
ml_template
机器学习项目模版-cookiecutter
nn_dqn-from-scratch
MLP-framework (pure numpy) and DQN-framework for OpenAI's Gym games.
nn_from_scratch
使用NumPy从头开始编写神经网络
onlineLearning
online learning
Optimx-Dashboard
Optimx mlops 可视化服务
Optimx-grad
Neural Network From Scratch
Optimx-Track
跟踪并共享人工智能实时实验、策略
reinforcement-learning-an-introduction
Python Implementation of Reinforcement Learning: An Introduction
RLLoadBalancer
modify the nginx configurations files without cli.
RLOps
rlops for real time rl models
single-ddqn-numpy
使用numpy的ddqn 高效实现
TinyNet
Neural Network From Scratch