winton1996 Goto Github PK

admm_python

Solomon benchmark instances

artificial-intelligence

SEU CS Artificial Intelligence Projects

awesome-graph-papers

Collect papers about graph

dqn-ddpg_stock_trading

Using DQN/DDPG for stock trading. Xiong, Z., Liu, X.Y., Zhong, S., Yang, H. and Walid, A., 2018. Practical deep reinforcement learning approach for stock trading, NeurIPS 2018 AI in Finance Workshop.

excel2latex

The Excel add-in for creating LaTeX tables

findpathonmap

配合博客的一些示例程序，博客地址https://blog.csdn.net/zjgo007

finrl-library

A Deep Reinforcement Learning Library for Automated Trading in Quantitative Finance. NeurIPS 2020. Please star. 🔥

finrl-meta

FinRL­-Meta: A Universe for Data­-Driven Financial Reinforcement Learning. 🔥

fpca

Python implementation of functional PCA - model

gnn_review

GNN综述阅读报告

gpsresilience

Use of taxi GPS devices as pervasive resilience sensors.

graphwave

machinelearning

My blogs and code for machine learning. http://cnblogs.com/pinard

matsim-example-project

A small example of how to use MATSim as a library.

matsim_synpp

Synthetic population pipeline code for eqasim

mm-algorithm

Solve some classical regression problem by MM algorithm

multimodal-due

A general formulation for multi-modal dynamic traffic assignment considering multi-class vehicles, public transit and parking

network-learning-via-multi-agent-inverse-transportation-problems

Despite the ubiquity of transportation data, statistical inference methods alone are not able to explain mechanistic relations within a network. Inverse optimization methods that capture network structure fulfill this gap, but they are designed to take observations of the same model to learn the parameters of that model. New inverse optimization models and supporting algorithms are proposed to learn the parameters of heterogeneous travelers’ route optimization such that the value of shared network resources (e.g. link capacity dual prices) can be inferred. The inferred values are internally consistent with each agent’s optimization program. We prove that the method can obtain unique dual prices for a network shared by these agents, in polynomial time. Three experiments are conducted. The first one, conducted on a 4-node network, verifies the methodology to obtain heterogeneous link cost parameters even when a mixed logit model cannot provide meaningful results. The second is a parameter recovery test on the Nguyen-Dupuis network that shows that unique latent link capacity dual prices can be inferred using the proposed method. The last test on the same network demonstrates how a monitoring system in an online learning environment can be designed using this method.

neurodynamicprogramming-mfd

Source code of the Neuro-dynamic programming approach for optimal control of Macroscopic fundamental diagram (MFD) system)

pingan_baseline

reinforcement-learning-with-tensorflow

Simple Reinforcement learning tutorials

sharecar_report

大数据看共享汽车——GoFun篇

spatio-temporal-paper-list

Spatio-temporal modeling 论文列表（主要是graph convolution相关)

stable-baselines3

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

stgcn

The PyTorch version of STGCN.

suisnotme.github.io

transportationnetworks

Transportation Networks for Research

umich_applied_data_science_with_python

velocity_control

Source code for paper "Safe, Efficient, and Comfortable Velocity Control based on Reinforcement Learning for Autonomous Driving"

wentaohuang.github.io

Wentao's personal website