IMP-MARL: a suite of environments for large-scale infrastructure management planning via MARL

[PDF] arxiv.org

Multi-agent deep reinforcement learning with centralized training and decentralized execution for transportation infrastructure management

M Saifullah, KG Papakonstantinou, CP Andriotis… - arXiv preprint arXiv …, 2024 - arxiv.org
We present a multi-agent Deep Reinforcement Learning (DRL) framework for managing
large transportation infrastructure systems over their life-cycle. Life-cycle management of …
被引用次数：9 相关文章 所有 3 个版本
[PDF] arxiv.org

MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning

F Felten, U Ucak, H Azmani, G Peng, W Röpke… - arXiv preprint arXiv …, 2024 - arxiv.org
Many challenging tasks such as managing traffic systems, electricity grids, or supply chains
involve complex decision-making processes that must balance multiple conflicting …
被引用次数：1 相关文章 所有 7 个版本
[PDF] arxiv.org

POGEMA: A Benchmark Platform for Cooperative Multi-Agent Navigation

A Skrynnik, A Andreychuk, A Borzilov… - arXiv preprint arXiv …, 2024 - arxiv.org
Multi-agent reinforcement learning (MARL) has recently excelled in solving challenging
cooperative and competitive multi-agent problems in various environments with, mostly, few …
被引用次数：1 相关文章 所有 4 个版本

基于多智能体强化学习的博弈综述

李艺春， 刘泽娇， 洪艺天， 王继超， 王健瑞， 李毅， 唐漾 - 自动化学报, 2024 - aas.net.cn
多智能体强化学习作为博弈论, 控制论和多智能体学习的交叉研究领域, 是多智能体系统研究中
的前沿方向, 赋予了智能体在动态多维的复杂环境中通过交互和决策完成多样化任务的能力 …
相关文章 所有 3 个版本
[PDF] arxiv.org

Episodic Future Thinking Mechanism for Multi-agent Reinforcement Learning

D Lee, M Kwon - arXiv preprint arXiv:2410.17373, 2024 - arxiv.org
Understanding cognitive processes in multi-agent interactions is a primary goal in cognitive
science. It can guide the direction of artificial intelligence (AI) research toward social …
相关文章 所有 3 个版本
[PDF] arxiv.org

Upside-Down Reinforcement Learning for More Interpretable Optimal Control

J Cardenas-Cartagena, M Falzari, M Zullich… - arXiv preprint arXiv …, 2024 - arxiv.org
Model-Free Reinforcement Learning (RL) algorithms either learn how to map states to
expected rewards or search for policies that can maximize a certain performance function …
相关文章 所有 4 个版本

Imap-gcg: Edge container resource scheduling and configuration method based on improved mappo and gcn-gru

X Gong, Y Yang, Y Sun, Z Gao, L Rui - International Conference on …, 2023 - Springer
Container technology has been widely used in industrial development, including system
deployment and program management, and has achieved very good results. However, in …
被引用次数：1 相关文章

Multi-Agent Reinforcement Learning for WEEE Recycling Vehicle Path Planning Based on Graph Attention Networks

Z Qv, Q Liang, M Li, Y Zhang, F Meng… - … Conference on New …, 2024 - ieeexplore.ieee.org
With the global surge in WEEE generation, optimizing vehicle routing for recycling has
become a critical area of research. This paper introduces a MARL method built upon graph …
相关文章