27,697 Hits in 4.0 sec

Non-Cooperative Energy Efficient Power Allocation Game in D2D Communication: A Multi-Agent Deep Reinforcement Learning Approach

Khoi Khac Nguyen, Trung Q Duong, Ngo Anh Vien, Nhien-An Le-Khac, Nghia M Nguyen
2019 IEEE Access  
INDEX TERMS Energy efficient wireless communication, power allocation, D2D communication, multiagent reinforcement learning, deep reinforcement learning.  ...  Our main contribution is to propose a novel non-cooperative and real-time approach based on deep reinforcement learning to deal with the energy-efficient power allocation problem while still satisfying  ...  At convergence, it seems that the performances of multi-agent double deep Q-learning and deep dueling deep Q-learning are comparable.  ... 
doi:10.1109/access.2019.2930115 fatcat:vuyjpjpumzamxhlulczi4hipwy

Human and Multi-Agent collaboration in a human-MARL teaming framework [article]

Neda Navidi, Francoi Chabo, Saga Kurandwa, Iv Lutigma, Vincent Robt, Gregry Szrftgr, Andea Schuh
2021 arXiv   pre-print
Reinforcement learning provides effective results with agents learning from their observations, received rewards, and internal interactions between agents.  ...  We demonstrate these innovations by using a designed real-time environment with unmanned aerial vehicles driven by RL agents, collaborating with a human.  ...  Multi-Agent Deep Deterministic Policy Gradient (MADDPG) algorithm is a general-purpose multi-agent deep reinforcement learning algorithm based on policy gradient method [15] .  ... 
arXiv:2006.07301v2 fatcat:3j3nrofctjezvfvuwrggwmq75y

Specializing Inter-Agent Communication in Heterogeneous Multi-Agent Reinforcement Learning using Agent Class Information [article]

Douglas De Rizzo Meneghetti, Reinaldo Augusto da Costa Bianchi
2021 arXiv   pre-print
Inspired by recent advances in agent communication with graph neural networks, this work proposes the representation of multi-agent communication capabilities as a directed labeled heterogeneous agent  ...  We also introduce a neural network architecture that specializes communication in fully cooperative heterogeneous multi-agent tasks by learning individual transformations to the exchanged messages between  ...  Deep Multi-Agent Reinforcement Learning Recent advances in the area of deep multi-agent reinforcement learning that contributed to this work are the network architectures trained with off-policy algorithms  ... 
arXiv:2012.07617v2 fatcat:up3b6kdo4nc5vhp3d5f33vpcdy

Learning Complex Multi-Agent Policies in Presence of an Adversary [article]

Siddharth Ghiya, Katia Sycara
2020 arXiv   pre-print
We address the requirements of such a setting by implementing a graph-based multi-agent deep reinforcement learning algorithm.  ...  In recent years, there has been some outstanding work on applying deep reinforcement learning to multi-agent settings. Often in such multi-agent scenarios, adversaries can be present.  ...  RELATED WORK There has been a recent surge in the application of deep learning to reinforcement learning.  ... 
arXiv:2008.07698v2 fatcat:uhy7zj3d7nhbpaj5u6xymj2pda

A Survey of Deep Reinforcement Learning in Video Games [article]

Kun Shao, Zhentao Tang, Yuanheng Zhu, Nannan Li, Dongbin Zhao
2019 arXiv   pre-print
Deep reinforcement learning (DRL) has made great achievements since proposed.  ...  single-agent to multi-agent.  ...  Reinforced Inter-Agent Learning (RIAL) and Differentiable Inter-Agent Learning (DIAL) use deep reinforcement learning to learn endto-end communication protocols in complex environments.  ... 
arXiv:1912.10944v2 fatcat:fsuzp2sjrfcgfkyclrsyzflax4

Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications [article]

Thanh Thi Nguyen, Ngoc Duy Nguyen, Saeid Nahavandi
2019 arXiv   pre-print
schemes, multi-agent transfer learning.  ...  This paper addresses an important aspect of deep RL related to situations that require multiple agents to communicate and cooperate to solve complex tasks.  ...  Each agent is learned by the dueling double deep Q-network (DDDQN), which integrates dueling networks, double DQN and prioritized experience replay.  ... 
arXiv:1812.11794v2 fatcat:dkmnfhdsrrepzd277nhzouymzq

Communicative Reinforcement Learning Agents for Landmark Detection in Brain Images [article]

Guy Leroy, Daniel Rueckert, Amir Alansary
2020 arXiv   pre-print
We propose a novel communicative multi-agent reinforcement learning (C-MARL) system to automatically detect landmarks in 3D brain images.  ...  Our experiments show that involving multiple cooperating agents by learning their communication with each other outperforms previous approaches using single agents.  ...  Contributions: (I) We propose a novel communicative multi-agent reinforcement learning for multiple landmarks detection.  ... 
arXiv:2008.08055v2 fatcat:3ubkgbcmbzaofi2m3sweb5n43u

Future Trends for Human-AI Collaboration: A Comprehensive Taxonomy of AI/AGI Using Multiple Intelligences and Learning Styles [article]

Andrzej Cichocki, Alexander P. Kuleshov
2020 arXiv   pre-print
Multi-agent systems such as these can be used to solve problems that would be difficult to solve by any individual intelligent agent.  ...  Future AI systems will be able not only to communicate with human users and each other, but also to efficiently exchange knowledge and wisdom with abilities of cooperation, collaboration and even co-creating  ...  Categorization of the State-of the Arts Machine Learning Algorithms: Supervised, Unsupervised, Reinforcement Learning, Ensemble Learning, Deep Learning and Deep Reinforcement Learning (a) (b)  ... 
arXiv:2008.04793v4 fatcat:4l4wxa3bwnhlfbkfp2i63uwaou

Hierarchical RNNs-Based Transformers MADDPG for Mixed Cooperative-Competitive Environments [article]

Xiaolong Wei, LiFang Yang, Xianglin Huang, Gang Cao, Tao Zhulin, Zhengyang Du, Jing An
2021 arXiv   pre-print
MARL (known as Multi-Agent Reinforcement Learning) can be recognized as a set of independent agents trying to adapt and learn through their way to reach the goal.  ...  At present, attention mechanism has been widely applied to the fields of deep learning models.  ...  In the field of multi-agent reinforcement learning, researchers have tried to add an attention mechanism, such as Iqbal [21] , which combines attention with MADDPG and achieved remarkable results.  ... 
arXiv:2105.04888v1 fatcat:m6bciz74bvh7vkw6fyzdes6mwe

Reinforcement Learning in Dynamic Task Scheduling: A Review

Chathurangi Shyalika, Thushari Silva, Asoka Karunananda
2020 SN Computer Science  
This review paper is about a research study that focused on Reinforcement Learning techniques that have been used for dynamic task scheduling.  ...  Reinforcement Learning is an emergent technology which has been able to solve the problem of the optimal task and resource scheduling dynamically.  ...  Compliance with ethical Standards Conflicts of Interest/Competing Interests The authors declare that there are no conflicts of interest regarding the publication of this article.  ... 
doi:10.1007/s42979-020-00326-5 fatcat:egp6vgpetbcwdasm45vunmo3n4

A novel multi-agent parallel-critic network architecture for cooperative-competitive reinforcement learning

Yu Sun, Jun Lai, Lei Cao, Xiliang Chen, Zhixiong Xu, Yue Xu
2020 IEEE Access  
INDEX TERMS multi-agent system, deep reinforcement learning, parallel-critic architecture, training stability.  ...  multi-agent deep reinforcement learning (MDRL) is an emerging research hotspot and application direction in the field of machine learning and artificial intelligence.  ...  Besides, attention communication MDRL [18] , ACCNet [19] , message pruning communication MDRL [20] , double attentional actorcritic message processor (DAACMP) [21] , attention-based message processing  ... 
doi:10.1109/access.2020.3011670 fatcat:lg2mey5re5er5f7tcwwagb66li

SSHA: Video Violence Recognition and Localization Using a Semi-Supervised Hard Attention Model [article]

Hamid Mohammadi, Ehsan Nazerfard
2022 arXiv   pre-print
Exceedingly efficient and precise machine learning models are required to effectively utilize the extensive volume of high-definition surveillance imagery.  ...  The semi-supervised hard attention mechanism has enabled the proposed method to fully capture the available information in a high-resolution video by processing the necessary video regions in great detail  ...  Extending the SSHA method of learning attention to a higher number of attention regions is possible by converting the problem to a multi-agent reinforcement learning problem.  ... 
arXiv:2202.02212v3 fatcat:n4amj7dzn5be5k5gl255hc7abi

Series Editorial The Fourth Issue of the Series on Machine Learning in Communications and Networks

Geoffrey Y. Li, Walid Saad, Ayfer Ozgur, Peter Kairouz, Zhijin Qin, Jakob Hoydis, Zhu Han, Deniz Gunduz, Jaafar Elmirghani
2022 IEEE Journal on Selected Areas in Communications  
HE third call for papers of the Series on Machine Learning in Communications and Networks has continued to receive a great number of high-quality papers covering various aspects of intelligent communications  ...  In [A2], Hussain and Michelusi provide an approach for beam training technique in mm-Wave systems with low overhead.  ...  The novel multi-agent deep reinforcement learning (MADRL) algorithm, namely, graph-embedded value-decomposition actorcritic (GE-VDAC), embeds the interaction information of agents, and learns a locally  ... 
doi:10.1109/jsac.2021.3126188 fatcat:6aohhlq55fco5gnndq6cusjbbi

Reinforcement Learning in Stock Trading [chapter]

Quang-Vinh Dang
2019 Advances in Intelligent Systems and Computing  
We compare the deep reinforcement learning approach with state-of-the-art supervised deep learning prediction in real-world data.  ...  Using machine learning techniques in financial markets, particularly in stock trading, attracts a lot of attention from both academia and practitioners in recent years.  ...  Nevertheless, with the development of the machine learning community, technical analysis gains attention of researchers in recent years.  ... 
doi:10.1007/978-3-030-38364-0_28 fatcat:jptwzdajwfcavmz3gzynctjd5i

Collaborative Edge Computing and Caching with Deep Reinforcement Learning Decision Agents

Jianji Ren, Haichao Wang, TingTing Hou, Shuai Zheng, Chaosheng Tang
2020 IEEE Access  
.: Collaborative Edge Computing and Caching with Deep Reinforcement Learning Decision Agents VOLUME 4, 2016 VOLUME 4, 2016  ...  COLLABORATIVE COMPUTING STRATEGY BASED ON DOUBLE DEEP Q-LEARNING In order to better understand the DDQN agent, we briefly introduce DDQN in this paper. First, we introduce reinforcement learning.  ...  CONCLUSION AND FUTURE WORK In this paper, we consider the bandwidth, computing, and cache resources of the ENs, benefit from the deep learning and powerful learning ability and decision-making characteristics  ... 
doi:10.1109/access.2020.3007002 fatcat:eetpyov3rjhkxgovhgw2qxfkv4
« Previous Showing results 1 — 15 out of 27,697 results