yxjkn7 Goto Github PK

adp_lp

LP approach for Approximate Dynamic Programming.

battery_dispatching_with_peak_demand_charges

Code for the paper "Battery Dispatching for End Users With On-Site Renewables and Peak Demand Charges - An Approximate Dynamic Programming Approach"

causally-regularized-learning

A method which takes advantage of causal features for classification

diagnosing-object-detectors

This project shows how to analyze the influences of object characteristics on detection performance and the frequency and impact of different types of false positives.

dnn-dp

Code for Deep Neural Network Approximated Dynamic Programming

drl-mtsp

Reinplemtation of paper "A reinforcement learning approach for optimizing multiple traveling salesman problems over graphs"

dual-adp-suc

Code / data for the paper "A Dual Approximate Dynamic Programming Approach for Multi-stage Stochastic Unit Commitment" http://www.optimization-online.org/DB_HTML/2018/06/6672.html

encode-attend-navigate

Learning Heuristics for the TSP by Policy Gradient

graph-pointer-network

lbpo

Lyapunov Barrier Policy Optimization

learningtocompare_fsl

PyTorch code for CVPR 2018 paper: Learning to Compare: Relation Network for Few-Shot Learning (Few-Shot Learning part)

mcts

Python Implementations of Monte Carlo Tree Search

ml-adp

Pytorch-Native Approximate Dynamic Programming for Finite-Horizon Discrete-Time Stochastic Optimal Control Problems

neuradp-for-ride-pooling

A simulator and learning agent to solve the ridesharing problem

online-vehicle-routing-drl

PyTorch implementation of Online Vehicle Routing With Neural Combinatorial Optimization and Deep Reinforcement Learning https://ieeexplore.ieee.org/document/8693516

parts-object-context

Code for "Objects as Context for Part Detection".

rainbow

Rainbow: Combining Improvements in Deep Reinforcement Learning

reinforcement_learning

This repository demonstrates a learning approach to the stabilization of a pendulum. Reinforcement Learning is used to learn a policy for balancing a pendulum in the upright position. Reinforcement Learning hereby refers to Approximate Dynamic Programming (ADP), a sampling based version of Dynamic Programming.

relation-networks-for-object-detection

Relation Networks for Object Detection

relation_networks-pytorch

Relation Networks for object detection based pytorch

rl-vrp-ptrntwrk

Reinforcement Learning for Solving the Vehicle Routing Problem

transferrl

Deep Transfer Reinforcement Learning for Text Summarization

vc-r-cnn

[CVPR 2020] The official pytorch implementation of ``Visual Commonsense R-CNN''

vehicle-routing-problem-gpu-cuda

This repo contains a source code in Python as well CUDA for VRP

vrp

A project of the paper "Online Vehicle Routing With Neural Combinatorial Optimization and Deep Reinforcement Learning"

vrp-rl

Reinforcement Learning for Solving the Vehicle Routing Problem

vrp_drl_mha

"Attention, Learn to Solve Routing Problems!"[Kool+, 2019], Capacitated Vehicle Routing Problem solver

what-if

教材 Causal Inference: What if 的编译和解读！