Open Access
Open access
Lecture Notes in Computer Science, volume 12948 LNAI, pages 169-179

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

Publication typeBook Chapter
Publication date2021-10-04
Quartile SCImago
Q3
Quartile WOS
Impact factor
ISSN03029743, 16113349, 18612075, 18612083
Abstract
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 full knowledge of the environment. To this end, 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 a large number of agents.

Citations by journals

1
PeerJ Computer Science
PeerJ Computer Science, 1, 100%
PeerJ Computer Science
1 publication, 100%
1

Citations by publishers

1
PeerJ
PeerJ, 1, 100%
PeerJ
1 publication, 100%
1
  • We do not take into account publications that without a DOI.
  • Statistics recalculated only for publications connected to researchers, organizations and labs registered on the platform.
  • Statistics recalculated weekly.
Metrics
Share
Cite this
GOST |
Cite this
GOST Copy
Davydov V. et al. Q-Mixing Network for Multi-agent Pathfinding in Partially Observable Grid Environments // Lecture Notes in Computer Science. 2021. Vol. 12948 LNAI. pp. 169-179.
GOST all authors (up to 50) Copy
Davydov V., Skrynnik A., Yakovlev K., Panov A. Q-Mixing Network for Multi-agent Pathfinding in Partially Observable Grid Environments // Lecture Notes in Computer Science. 2021. Vol. 12948 LNAI. pp. 169-179.
RIS |
Cite this
RIS Copy
TY - GENERIC
DO - 10.1007/978-3-030-86855-0_12
UR - https://doi.org/10.1007%2F978-3-030-86855-0_12
TI - Q-Mixing Network for Multi-agent Pathfinding in Partially Observable Grid Environments
T2 - Lecture Notes in Computer Science
AU - Davydov, Vasilii
AU - Skrynnik, Alexey
AU - Yakovlev, Konstantin
AU - Panov, Aleksandr
PY - 2021
DA - 2021/10/04 00:00:00
PB - Springer Nature
SP - 169-179
VL - 12948 LNAI
SN - 0302-9743
SN - 1611-3349
SN - 1861-2075
SN - 1861-2083
ER -
BibTex
Cite this
BibTex Copy
@incollection{2021_Davydov
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},
publisher = {Springer Nature},
year = {2021},
volume = {12948 LNAI},
pages = {169--179},
month = {oct}
}
Found error?