Open Access
Open access

Q-Mixing Network for Multi-agent Pathfinding in Partially Observable Grid Environments

Davydov V., Skrynnik A., Yakovlev K., Panov A.
Тип документаBook Chapter
Дата публикации2021-01-01
Название журналаLecture Notes in Computer Science
ИздательSpringer Nature
КвартильQ3
ISSN03029743, 16113349
Краткое описание
In this paper, we consider the problem of multi-agent navigation in partially observable grid environments. This problem is challenging for centralized planning approaches as they, typically, rely on the full knowledge of the environment. We suggest utilizing the reinforcement learning approach when the agents, first, learn the policies that map observations to actions and then follow these policies to reach their goals. To tackle the challenge associated with learning cooperative behavior, i.e. in many cases agents need to yield to each other to accomplish a mission, we use a mixing Q-network that complements learning individual policies. In the experimental evaluation, we show that such approach leads to plausible results and scales well to large number of agents.
Пристатейные ссылки: 19
Метрики
Поделиться
Цитировать
ГОСТ |
Цитировать
1. Davydov V. и др. Q-Mixing Network for Multi-agent Pathfinding in Partially Observable Grid Environments // Lecture Notes in Computer Science. 2021. С. 169–179.
RIS |
Цитировать

TY - GENERIC

DO - 10.1007/978-3-030-86855-0_12

UR - http://dx.doi.org/10.1007/978-3-030-86855-0_12

TI - Q-Mixing Network for Multi-agent Pathfinding in Partially Observable Grid Environments

T2 - Artificial Intelligence

AU - Davydov, Vasilii

AU - Skrynnik, Alexey

AU - Yakovlev, Konstantin

AU - Panov, Aleksandr

PY - 2021

PB - Springer International Publishing

SP - 169-179

SN - 0302-9743

SN - 1611-3349

ER -

BibTex |
Цитировать

@incollection{Davydov_2021,

doi = {10.1007/978-3-030-86855-0_12},

url = {https://doi.org/10.1007%2F978-3-030-86855-0_12},

year = 2021,

publisher = {Springer International Publishing},

pages = {169--179},

author = {Vasilii Davydov and Alexey Skrynnik and Konstantin Yakovlev and Aleksandr Panov},

title = {Q-Mixing Network for Multi-agent Pathfinding in Partially Observable Grid Environments},

booktitle = {Artificial Intelligence}

}

MLA
Цитировать
Davydov, Vasilii et al. “Q-Mixing Network for Multi-Agent Pathfinding in Partially Observable Grid Environments.” Lecture Notes in Computer Science (2021): 169–179. Crossref. Web.