A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2021; you can also visit the original URL.
The file type is application/pdf
.
Filters
Cooperative Multi-Agent Reinforcement Learning Based Distributed Dynamic Spectrum Access in Cognitive Radio Networks
[article]
2021
arXiv
pre-print
on cooperative multi-agent reinforcement learning (MARL). ...
In this paper, we investigate the distributed DSA problem for multi-user in a typical multi-channel cognitive radio network. ...
Different from single-agent reinforcement learning in which the state transition of the environment switches based on its own action only, the new environment state of the multi-agent system is based on ...
arXiv:2106.09274v1
fatcat:cb5767uktrespkeoqmsvh2bxpq
Intelligence Through Interaction: Towards a Unified Theory for Learning
[chapter]
2007
Lecture Notes in Computer Science
and control (reinforcement learning). ...
, learning by instruction, and learning by reinforcement. ...
The generic network dynamics of fusion ART, based on fuzzy ART operations [4] , is summarized as follows. ...
doi:10.1007/978-3-540-72383-7_128
fatcat:2qwsva5ujvfahlzwntn4mfer2u
Series Editorial: The Third Issue of the Series on Machine Learning in Communications and Networks
2021
IEEE Journal on Selected Areas in Communications
The paper, titled "Joint Deep Reinforcement Learning and Unfolding: Beam Selection and Precoding for mmWave Multiuser MIMO with Lens Arrays," by Hu et al., uses deep reinforcement learning (DRL) for the ...
Learning in Communications and Networks has continued to receive a great number of high-quality papers covering various aspects of intelligent communication systems. ...
in communications by considering multiple agents communicating over a noisy channel under the multi-agent reinforcement learning (MARL) framework. ...
doi:10.1109/jsac.2021.3087366
fatcat:57l7wm4lljgt5n2ogqqlze6gvm
Priority-based reserved spectrum allocation by multi-agent through reinforcement learning in cognitive radio network
2019
Automatika
A novel priority-based reserved allocation method with a multi-agent system is proposed for spectrum allocation. ...
The multi-agent system performs the task of gathering environmental artefacts used for decision making to give the best of effort service in this adaptive communication. ...
Reinforcement learning Reinforcement learning (RL) is the AI technique that supports the multi-agent system by helping the agent to study the environment and take decision on a trial-anderror basis, to ...
doi:10.1080/00051144.2019.1674512
fatcat:fydssqrdongyzntxh2qv4cnfqq
A self-organizing multi-memory system for autonomous agents
2012
The 2012 International Joint Conference on Neural Networks (IJCNN)
The proposed system, employing fusion Adaptive Resonance Theory (fusion ART) network as a building block, consists of a declarative memory module, that learns both episodic traces and semantic knowledge ...
in real time, as well as a procedural memory module that learns reactive responses to its environment through reinforcement learning. ...
Fusion ART Fusion ART network is used to learn the individual memory modules in a unified manner. In this case, each memory trace stored is represented as a multi-channel pattern. ...
doi:10.1109/ijcnn.2012.6252429
dblp:conf/ijcnn/WangSTT12
fatcat:6x46xipqpvac7jepgukxdy3tsa
Multi-agent Attention Actor-Critic Algorithm for Load Balancing in Cellular Networks
[article]
2023
arXiv
pre-print
In cellular networks, User Equipment (UE) handoff from one Base Station (BS) to another, giving rise to the load balancing problem among the BSs. ...
This paper formulates the load balancing problem as a Markov game and proposes a Robust Multi-agent Attention Actor-Critic (Robust-MA3C) algorithm that can facilitate collaboration among the BSs (i.e., ...
The evaluation results demonstrate that Robust-MA3Ccan achieve superior performance over the rulebased and other multi-agent reinforcement learning algorithms on three key network performance metrics. ...
arXiv:2303.08003v1
fatcat:5pvzah2jxjewrkfzidsqnxh45i
DYNAMIC AND INCREMENTAL EXPLORATION STRATEGY IN FUSION ADAPTIVE RESONANCE THEORY FOR ONLINE REINFORCEMENT LEARNING
2016
Jurnal Ilmu Komputer dan Informasi
This paper presents a type of multi-channel adaptive resonance theory (ART) neural network model called fusion ART which serves as a fuzzy approximator for reinforcement learning with inherent features ...
One of the fundamental challenges in reinforcement learning is to setup a proper balance between exploration and exploitation to obtain the maximum cummulative reward in the long run. ...
Fusion ART Dynamics A multi-channel ART is a variant of ART network that incorporate multiple input (output) neural fields. ...
doi:10.21609/jiki.v9i2.380
fatcat:u2q7hsqc6jevhdyh77ggkidnhq
Guest editorial: Time-critical communication and computation for intelligent vehicular networks
2021
China Communications
This article proposes a Multi-Agent Reinforcement Learning (MARL) based decentralized routing scheme, where the inherent similarity between the routing problem in vehicular ad hoc network and the MARL ...
The feature topic begins with the article by Lu et al., "MARVEL: multi-agent reinforcement learning for VANET delay minimization". ...
This article proposes a Multi-Agent Reinforcement Learning (MARL) based decentralized routing scheme, where the inherent similarity between the routing problem in vehicular ad hoc network and the MARL ...
doi:10.23919/jcc.2021.9459559
fatcat:rzkn2kcbvfanzjvwrly7sgmvlu
Agent-Augmented Co-Space: Toward Merging of Real World and Cyberspace
[chapter]
2010
Lecture Notes in Computer Science
Following the notion of embodied intelligence, we propose to develop cognitive agents, based on a family of self-organizing neural models, known as fusion Adaptive Resonance Theory (fusion ART). ...
With the advancement in pervasive sensor network, Co-Space may also capture and mirror the happening in the physical world in real time. ...
The generic network dynamics of fusion ART, based on fuzzy ART operations [6] , is summarized as follows. ...
doi:10.1007/978-3-642-16576-4_22
fatcat:tw3b6hjzpjfedmmet527vjpfoi
FCMNet: Full Communication Memory Net for Team-Level Cooperation in Multi-Agent Systems
[article]
2022
arXiv
pre-print
We introduce FCMNet, a reinforcement learning based approach that allows agents to simultaneously learn a) an effective multi-hop communications protocol and b) a common, decentralized policy that enables ...
There, our comparison results show that FCMNet outperforms state-of-the-art communication-based reinforcement learning methods in all StarCraft II micromanagement tasks, and value decomposition methods ...
We would like to thank Mehul Damani and Benjamin Freed for their feedback on earlier drafts of this paper. ...
arXiv:2201.11994v2
fatcat:5l7gwvowkjf5zagejwhminwpau
Exploration and Communication for Partially Observable Collaborative Multi-Agent Reinforcement Learning
2022
International Joint Conference on Autonomous Agents & Multiagent Systems
Multi-agent reinforcement learning (MARL) enables us to create adaptive agents in challenging environments, even when the agents have limited observation. ...
The next parts of my research will focus on multi-agent exploration and learning to communicate. ...
CONCLUSION
My research focuses on collaborative Multi-Agent Reinforcement Learning and is built around three main axes. ...
dblp:conf/atal/Avalos22
fatcat:xil52ml36rbdfhgyhbogidxowa
Multi Agent Deep Learning with Cooperative Communication
2020
Journal of Artificial Intelligence and Soft Computing Research
AbstractWe consider the problem of multi agents cooperating in a partially-observable environment. Agents must learn to coordinate and share relevant information to solve the tasks successfully. ...
We compare and show that A3C2 outperforms other state-of-the-art proposals in multiple environments. ...
This work was financially supported by: Base Funding -UIDB/00027/2020 of the Artificial Intelligence and Computer Science Laboratory -LIACC -funded by national funds through the FCT/MCTES (PID-DAC). ...
doi:10.2478/jaiscr-2020-0013
fatcat:oehr25sfardffihup2goyrqyoa
Constrained Deep Reinforcement Learning for Energy Sustainable Multi-UAV based Random Access IoT Networks with NOMA
[article]
2020
arXiv
pre-print
based on Lagrangian primal-dual policy optimization to solve the CMDP. ...
To enable an energy-sustainable capacity-optimal network, we study the joint problem of dynamic multi-UAV altitude control and multi-cell wireless channel access management of IoT devices as a stochastic ...
CONCLUSION In this paper, we have applied constrained deep reinforcement learning to study the joint problem of dynamic multi-UAV altitude control and random channel access management of a multi-cell UAV-based ...
arXiv:2002.00073v2
fatcat:igm45qcklvbkfe7mnwapabb4k4
MAPPER: Multi-Agent Path Planning with Evolutionary Reinforcement Learning in Mixed Dynamic Environments
[article]
2020
arXiv
pre-print
planner LRA* and the state-of-the-art learning-based method. ...
Reinforcement learning-based methods usually suffer performance degradation on long-horizon tasks with goal-conditioned sparse rewards, so we decompose the long-range navigation task into many easier sub-tasks ...
Multi-Agent Evolutionary Reinforcement Learning Although reinforcement learning has achieved great success in many single-agent tasks [25] , it is still hard to directly apply those methods to the multi-agent ...
arXiv:2007.15724v1
fatcat:iq2bgtpfsnhy3p2naq4cvlb4me
Machine Learning in Beyond 5G/6G Networks—State-of-the-Art and Future Trends
2021
Electronics
Artificial Intelligence (AI) and especially Machine Learning (ML) can play a very important role in realizing and optimizing 6G network applications. ...
These methods include supervised, unsupervised and reinforcement techniques. ...
In [96] , the authors propose a multi-agent deep reinforcement learning-based model, named Neighbor-Agent Actor Critic (NAAC), for spectrum allocation in 6G network D2D scenarios. ...
doi:10.3390/electronics10222786
fatcat:6umid7qnabdttkjyhglpxjpwpm
« Previous
Showing results 1 — 15 out of 30,877 results