Filters








17,217 Hits in 6.0 sec

An adaptive synchronization approach for weights of deep reinforcement learning [article]

S. Amirreza Badran, Mansoor Rezghi
2020 arXiv   pre-print
In this paper, we address this problem from the DQN family and provide an adaptive approach for the synchronization of the neural weights used in DQN.  ...  Deep Q-Networks (DQN) is one of the most well-known methods of deep reinforcement learning, which uses deep learning to approximate the action-value function.  ...  Because of adaptability of our synchronization method, we call our modified DQN agent the Adaptive Synchronization DQN or for short AS_DQN and our modified Rainbow agent, AS_Rainbow.  ... 
arXiv:2008.06973v1 fatcat:l45ipnep7jfjzdmmmeawpog6pe

2021 Index IEEE Transactions on Neural Networks and Learning Systems Vol. 32

2021 IEEE Transactions on Neural Networks and Learning Systems  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  The primary entry includes the coauthors' names, the title of the paper or other item, and its location, specified by the publication abbreviation, year, month, and inclusive pagination.  ...  Event-Triggered Adaptive Optimal Control With Output Feedback: An Adaptive Dynamic Programming Approach.  ... 
doi:10.1109/tnnls.2021.3134132 fatcat:2e7comcq2fhrziselptjubwjme

2020 Index IEEE Transactions on Cybernetics Vol. 50

2020 IEEE Transactions on Cybernetics  
., Reference Trajectory Reshaping Optimi-zation and Control of Robotic Exoskeletons for Human-Robot Co-Manipulation; TCYB Aug. 2020 3740-3751 Wu, X., Jiang, B., Yu, K., Miao, c., and Chen, H  ...  ., +, Echo State Network-Based Backstepping Adaptive Iterative Learning Control for Strict-Feedback Systems: An Error-Tracking Approach.  ...  NN Reinforcement Learning Adaptive Control for a Class of Nonstrict-Feedback Discrete-Time Systems.  ... 
doi:10.1109/tcyb.2020.3047216 fatcat:5giw32c2u5h23fu4drupnh644a

Distributed Deep Reinforcement Learning: Learn How to Play Atari Games in 21 minutes [chapter]

Igor Adamski, Robert Adamski, Tomasz Grel, Adam Jędrych, Kamil Kaczmarek, Henryk Michalewski
2018 Lecture Notes in Computer Science  
We present a study in Distributed Deep Reinforcement Learning (DDRL) focused on scalability of a state-of-the-art Deep Reinforcement Learning algorithm known as Batch Asynchronous Advantage Actor-Critic  ...  We show that using the Adam optimization algorithm with a batch size of up to 2048 is a viable choice for carrying out large scale machine learning computations.  ...  For an in-depth review of scalability of modern supervised learning approaches, we refer the reader to [17] .  ... 
doi:10.1007/978-3-319-92040-5_19 fatcat:armgndw6u5afvcpg64rl2kyqk4

Distributed Deep Reinforcement Learning: Learn how to play Atari games in 21 minutes [article]

Igor Adamski, Robert Adamski, Tomasz Grel, Adam Jędrych, Kamil Kaczmarek, Henryk Michalewski
2018 arXiv   pre-print
We present a study in Distributed Deep Reinforcement Learning (DDRL) focused on scalability of a state-of-the-art Deep Reinforcement Learning algorithm known as Batch Asynchronous Advantage ActorCritic  ...  We show that using the Adam optimization algorithm with a batch size of up to 2048 is a viable choice for carrying out large scale machine learning computations.  ...  For an in-depth review of scalability of modern supervised learning approaches we refer the reader to [17] .  ... 
arXiv:1801.02852v2 fatcat:j4sxm4xjpjeh7iuro327tgvabi

2020 Index IEEE Transactions on Neural Networks and Learning Systems Vol. 31

2020 IEEE Transactions on Neural Networks and Learning Systems  
The Author Index contains the primary entry for each item, listed under the first author's name.  ...  The primary entry includes the coauthors' names, the title of the paper or other item, and its location, specified by the publication abbreviation, year, month, and inclusive pagination.  ...  Distributed Fault-Tolerant Control of Multiagent Systems: An Adaptive Learning Approach.  ... 
doi:10.1109/tnnls.2020.3045307 fatcat:34qoykdtarewhdscxqj5jvovqy

Control of neural systems at multiple scales using model-free, deep reinforcement learning

B. A. Mitchell, L. R. Petzold
2018 Scientific Reports  
Acknowledgements We are grateful for partial funding from the Institute for Collaborative Biotechnologies through grant W911NF-09-0001 from the U.S. Army Research Office the U.S.  ...  The views, opinions, and/ or findings expressed are those of the author(s) and should not be interpreted as representing the official views or policies of the Department of Defense or the U.S.  ...  To circumvent these issues, we adapt a model-free method from the reinforcement learning literature, Deep Deterministic Policy Gradients (DDPG).  ... 
doi:10.1038/s41598-018-29134-x pmid:30013195 pmcid:PMC6048054 fatcat:2e572sh3tzhrjeccag3t4oyxua

Series Editorial: The Third 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
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  ...  beam selection and deep-unfolding neural network (NN) for the digital precoding optimization.  ...  The paper, titled "Deep Active Learning Approach to Adaptive Beamforming for mmWave Initial Alignment," by Sohrabi et al., works on a DL approach to the adaptive and sequential beamforming design problem  ... 
doi:10.1109/jsac.2021.3087366 fatcat:57l7wm4lljgt5n2ogqqlze6gvm

Table of contents

2021 IEEE Transactions on Neural Networks and Learning Systems  
Sun Learning Automata-Based Multiagent Reinforcement Learning for Optimization of Cooperative Tasks ................. ...................................................................................  ...  Li Robust Formation Control for Cooperative Underactuated Quadrotors via Reinforcement Learning ..................... ...................................................................................  ... 
doi:10.1109/tnnls.2021.3112415 fatcat:76cvoarxv5gfxca5ziikpsss5m

Dimmer: Self-Adaptive Network-Wide Flooding with Reinforcement Learning [article]

Valentin Poirot, Olaf Landsiedel
2021 arXiv   pre-print
The last decade saw an emergence of Synchronous Transmissions (ST) as an effective communication paradigm in low-power wireless networks.  ...  We introduce Dimmer as a self-adaptive ST protocol. Dimmer builds on LWB and uses Reinforcement Learning to tune its parameters and match the current properties of the wireless medium.  ...  Through the use of deep reinforcement learning, from [22] R. Jacob, J. Baechli, R. D.  ... 
arXiv:2012.03719v2 fatcat:wvkpzkkxmvhgddc2jrum6z4bwe

Table of contents

2020 IEEE Transactions on Neural Networks and Learning Systems  
Gnaneswaran 4726 A Deep Supervised Learning Framework for Data-Driven Soft Sensor Modeling of Industrial Processes .............. .......................................................................  ...  Shao, and X A Learning-Based Solution for an Adversarial Repeated Game in Cyber-Physical Power Systems ..................... ............................................................................  ... 
doi:10.1109/tnnls.2020.3030506 fatcat:fnp55kp7orandbtqp3oebxuj6i

Special Issue on Deep Reinforcement Learning and Adaptive Dynamic Programming

Dongbin Zhao, Derong Liu, F. L. Lewis, Jose C. Principe, Stefano Squartini
2018 IEEE Transactions on Neural Networks and Learning Systems  
Editorial Special Issue on Deep Reinforcement Learning and Adaptive Dynamic Programming I N THE first issue of Nature 2015, Google DeepMind published a paper "Human-level control through deep reinforcement  ...  For data-based-constrained optimal control problems in the case of nonaffine nonlinear DT systems, B. Luo, D. Liu, and H. N. Wu develop an adaptive optimal control approach.  ... 
doi:10.1109/tnnls.2018.2818878 pmid:29993895 fatcat:iph6h5u2fvf5dixbml4jtfqk34

Asynchronous Methods for Model-Based Reinforcement Learning [article]

Yunzhi Zhang, Ignasi Clavera, Boren Tsai, Pieter Abbeel
2019 arXiv   pre-print
In this work, we propose an asynchronous framework for model-based reinforcement learning methods that brings down the run time of these algorithms to be just the data collection time.  ...  Significant progress has been made in the area of model-based reinforcement learning.  ...  Conclusion In this work we proposed an asynchronous framework for model-based reinforcement learning.  ... 
arXiv:1910.12453v1 fatcat:elu5qvs4pjddhoplcvkgomgjty

IEEE Access Special Section Editorial: Artificial Intelligence and Cognitive Computing for Communication and Network

Yin Zhang, Giancarlo Fortino, Limei Peng, Iztok Humar, Jianshan Sun
2020 IEEE Access  
, e.g., statistical learning, feedforward neural networks, deep recurrent neural networks, etc., for complicated decision making, network management, resource optimization, and in-depth knowledge discovery  ...  Under the new service paradigm, artificial intelligence (AI) and cognitive computing are very promising approaches for dealing with dynamic and large-scale topology; thus, we should explore AI-based techniques  ...  rate adaptation framework based on enhanced deep Q-learning.  ... 
doi:10.1109/access.2020.3014475 fatcat:z3xpk3x7ofhjbf7vmj2glozx6y

Table of contents

2021 IEEE Transactions on Neural Networks and Learning Systems  
Xie Reinforcement Learning-Based Optimal Tracking Control of an Unknown Unmanned Surface Vehicle ................ ....................................................................................  ...  Tan 2847 Semisupervised Learning on Graphs With an Alternating Diffusion Process .......... Q. Li, S. An, W. Liu, and L.  ... 
doi:10.1109/tnnls.2021.3089399 fatcat:5eehdq2lqvfwxnb6a5ub72evje
« Previous Showing results 1 — 15 out of 17,217 results