phil610351 Goto Github PK

rl_gnn

一个基于图神经网络的强化学习网络资源分配模型

rl_multi_agent_passage

Repository containing RL environment, model and trainer for GNN demo for ICRA 2022 paper "A Framework for Real-World Multi-Robot Systems\\Running Decentralized GNN-Based Policies"

rl_paper

rl_transmission_control

rmaddpg

ICML 2019 RL for Real Life Workshop: Recurrent MADDPG for Partially Observable and Limited Communication Settings

rnn-rl

Experiments with reinforcement learning and recurrent neural networks

roadnetsz

rome_mvs

The mobile vehicles (MVs) trajectories in the Rome city.

rome_mvs_trs

The mobile vehicles (MVs) trajectories in the Roman city.

rsdql

Microservice Deployment in Edge Computing Based on Deep Q Learning 作者：Lv W, Wang Q, Yang P, et al. 来源：IEEE Transactions on Parallel and Distributed Systems, 2022 摘要：微服务部署策略有望减少面向微服务的边缘计算平台中的整体服务响应时间。然而，现有的工作忽略了微服务之间交互频率不同的影响，以及节点负载增加导致的服务执行性能下降。在本文中，我们首先将微服务之间的调用关系建模为无向且加权的交互图来表征通信开销。然后，我们提出了边缘计算中的多目标微服务部署问题（MMDP）。MMDP旨在最小化通信开销，同时实现边缘节点之间的负载平衡。在不需要领域专家的情况下，我们提出了一种基于学习的算法奖励共享深度Q学习(RSDQL)来解决MMDP并获得最优部署策略。此外，为了提高服务的可扩展性，我们提出了一种基于启发式的弹性伸缩算法（ES）来处理请求的动态压力。最后，我们在Kubernetes中进行了一系列实验来评估我们方法的性能。实验结果表明，与交互感知策略和Kubernetes默认策略相比，RSDQL具有更短的响应时间，更均衡的资源负载，并且可以根据请求压力弹性扩展服务。

s-mfrl

The source code for the paper "S-MFRL: Spiking Mean Field Reinforcement Learning for Dynamic Resource Allocation of D2D Networks"

safe-policy-optimization

This is a benchmark repository for safe reinforcement learning algorithms

sarnet

Code repository for SARNet: Learning Multi-Agent Communication through Structured Attentive Reasoning (NeurIPS 2020)

sched_net

self-supervised-rl

transfer learing rl

sept

Single Episode Policy Transfer in Reinforcement Learning

service-migration-mdp

Code for paper "Dynamic Service Migration in Mobile Edge Computing Based on Markov Decision Process"

serviceplacement

share-parking_availability_prediction-pytorch

Semi-Supervised Hierarchical Recurrent Graph Neural Network for City-Wide Parking Availability Prediction

shared

simulator

Efficient Large-Scale Fleet Management via Multi-Agent Deep Reinforcement Learning

socom

A semi-online Computational Offloading Model, which utilizes users’ behavior prediction method to optimize task offloading in edge computing environments.

soft-module

Code for "Multi-task Reinforcement Learning with Soft Modularization"

sourcecodes_fog-edge_mangement

Fog/Edge management: A survey of source codes

spatio-temporal-matching-network

Interpretive Spatio-Temporal Features for Multi-Turn Responses Selection

spectrum-power-allocation

Deep Reinforcement Learning for Joint Spectrum and Power Allocation in Cellular Networks code

st-mgcn

[AAAI'19] Spatiotemporal Multi-Graph Convolution Network for Ride-Hailing Demand Forecasting (Pytorch Replication)

stam

Source code and dataset for WWW'22 paper "STAM: A Spatiotemporal Aggregation Method for Graph Neural Network-based Recommendation"

star

[ECCV 2020] Code for "Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction"

starcraft

Implementations of IQL, QMIX, VDN, COMA, QTRAN, MAVEN, CommNet, DyMA-CL, and G2ANet on SMAC, the decentralised micromanagement scenario of StarCraft II