1,997 Hits in 31.4 sec

Multi-Automata Learning [chapter]

Verbeeck Katja, Nowe Ann, Vrancx Peter, Peeters Maarte
2008 Reinforcement Learning  
So a key question in multi-agent Reinforcement Learning (MARL) is how multiple reinforcement learning agents can learn optimal behavior under constraints such as high communication costs.  ...  Conclusion In this chapter we have demonstrated that Learning Automata are interesting building blocks for multi-agent Reinforcement learning algorithms.  ... 
doi:10.5772/5280 fatcat:iuf4kknmqfeinikbockhyromgu

Utilizing Learning Automata and Entropy to Improve the Exploration Power of Rescue Agents

Behrooz Masoumi, Mostafa Asghari, Mohammad Reza Meybodi
2010 2010 Second WRI Global Congress on Intelligent Systems  
In this paper we present an exploration method based on variable structure S model learning automaton which uses the entropy of action's probability vector as a criteria to give reward or to penalize its  ...  This method can leads agents to establish a logical balance between exploration and exploitation too.  ...  In order to be able to use entropy as a reinforcement signal for S-Model variable structure learning automata, the entropy needs to be rescaled in the range of [0,1].  ... 
doi:10.1109/gcis.2010.9 fatcat:7j6r6iy4tzeareycqmlzlepl4a

Formalizing Multi-state Learning Dynamics

Daniel Hennes, Karl Tuyls, Matthias Rauterberg
2008 2008 IEEE/WIC/ACM International Conference on Web Intelligence and Intelligent Agent Technology  
This paper extends the link between evolutionary game theory and multi-agent reinforcement learning to multistate games.  ...  These definitions are general in the number of agents and states. Results show that piecewise replicator dynamics qualitatively approximate multi-agent reinforcement learning in stochastic games.  ...  Convergence for learning automata in single and specific multi-agent cases has been proven in [3] .  ... 
doi:10.1109/wiiat.2008.33 dblp:conf/iat/HennesTR08 fatcat:y4ohob5mrndnzatpjonvai3jly

Optimizing Dialogue Strategy Learning Using Learning Automata

G. Kumaravelan, R. Sivakumar
2009 Zenodo  
Hence we present a model-based online policy learning algorithm using interconnected learning automata for optimizing dialogue strategy.  ...  Researchers have mostly focused on model-free algorithms for automating the design of dialogue management using machine learning techniques such as reinforcement learning.  ...  In Q-leaning approach with multi agent setup, each agent uses an epsilon greedy exploration strategy with a standard single agent Q-leaning rule as: γ max a, Q i (s , a ) ) (10) Each Q-learner learns  ... 
doi:10.5281/zenodo.1079060 fatcat:pqf5btiesnhexdr37glivu76lm

Reinforcement Learning Algorithms for Uncertain, Dynamic, Zero-Sum Games

Snehasis Mukhopadhyay, Omkar Tilak, Subir Chakrabarti
2018 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA)  
A novel algorithm, based on heterogeneous games of learning automata (HEGLA), as well as algorithms based on model-based and model-free reinforcement learning, are presented as possible approaches to learning  ...  In this paper, we derive a sufficient condition for the existence of a solution to this problem, and then proceed to discuss various reinforcement learning strategies to solve such a dynamic game in the  ...  This now forms much of the formal basis to the recent field of multi-agent reinforcement learning. [4] is a special journal issue consisting of several papers in the area of learning and computational  ... 
doi:10.1109/icmla.2018.00015 dblp:conf/icmla/MukhopadhyayTC18 fatcat:hfxkxlhjnrbz7ln33n3ogiwesi

A Novel Learning Algorithm Based on a Multi-Agent Structure for Solving Multi-Mode Resource-Constrained Project Scheduling Problem [chapter]

Omid Mirzaei, Mohammad-R. Akbarzadeh-T.
2012 Lecture Notes in Electrical Engineering  
This paper tries to introduce a new multi-agent learning algorithm (MALA) for solving the multi-mode resource-constrained project scheduling problem (MMRCPSP), in which the activities of the project can  ...  The experimental results show that our method is a new one for this specific problem and can outperform other algorithms in different areas.  ...  Considering this matter, a motivation for using them is that they are excellent tools for multi-agent reinforcement learning solutions [14] .  ... 
doi:10.1007/978-94-007-5699-1_24 fatcat:p6p7utspcvhbno3htxmna726iu

Reinforcement learning for human-machine collaborative optimization: Application in ground water monitoring

Meghna Babbar-Sebens, Snehasis Mukhopadhyay
2009 2009 IEEE International Conference on Systems, Man and Cybernetics  
In this paper, we introduce reinforcement learning as a methodology to solve complex multi-criteria optimization problems for ground water monitoring.  ...  Different learning automata based reinforcement learning methods as well as a genetic algorithm based method are used in experimental studies, which demonstrate the efficiency of reinforcement learning  ...  In this paper, we formulate a groundwater monitoring problem as an identical pay-off game of multiple reinforcement learning agents, each using a conceptually simple learning algorithm.  ... 
doi:10.1109/icsmc.2009.5346708 dblp:conf/smc/Babbar-SebensM09 fatcat:6s5podhbkjh4dkcnkurbrlwlqi

Reinforcement Learning based Routing Protocols in WSNs: A Survey

Anju Arya
2018 International Journal for Research in Applied Science and Engineering Technology  
This paper provides a brief overview of the routing protocols using Reinforcement learning approach for WSNs. Keywords-Reinforcement Learning (RL), Wireless Sensor Network (WSN), Routing Protocols.  ...  The remaining sections provides a brief overview about the routing protocols for WSNs based on Reinforcement Learning approach.  ...  On the basis of coordinating agent To get a more accurate model for a large number of sensor nodes, a multi-agent system approach can to be adopted.  ... 
doi:10.22214/ijraset.2018.4584 fatcat:5m57uwekobh2nltvnntxlfti6q

Evolutionary Dynamics of Multi-Agent Learning: A Survey

Daan Bloembergen, Karl Tuyls, Daniel Hennes, Michael Kaisers
2015 The Journal of Artificial Intelligence Research  
The past two decades have seen the emergence of reinforcement learning, both in single and multi-agent settings, as a strong, robust and adaptive learning paradigm.  ...  This article surveys the dynamical models that have been derived for various multi-agent reinforcement learning algorithms, making it possible to study and compare them qualitatively.  ...  Acknowledgments We are grateful to the editor and anonymous reviewers of JAIR for their valuable feedback and helpful suggestions.  ... 
doi:10.1613/jair.4818 fatcat:6wqvs63nezd6xfz3zf7c4cattq

A cooperative learning method based on cellular learning automata and its application in optimization problems

Milad Mozafari, Mohammad Ebrahim Shiri, Hamid Beigy
2015 Journal of Computational Science  
In this paper, a novel reinforcement learning method inspired by the way humans learn from others is presented.  ...  This method is developed based on cellular learning automata featuring a modular design and cooperation techniques.  ...  Our method benefits from advantages of both LAs that use reinforcement learning techniques, and CA as a tool for parallelism and a basis 30 for modeling the fact that human decisions are influenced by  ... 
doi:10.1016/j.jocs.2015.08.002 fatcat:77ukoubsrnh57h4crcnoiadyfe

Multi-agent Learning Dynamics: A Survey [chapter]

H. Jaap van den Herik, D. Hennes, M. Kaisers, K. Tuyls, K. Verbeeck
2007 Lecture Notes in Computer Science  
In this paper we compare state-of-the-art multi-agent reinforcement learning algorithms in a wide variety of games. We consider two types of algorithms: value iteration and policy iteration.  ...  Multiple visualizations are included to provide a comprehensive insight into the learning dynamics.  ...  background information on multi-agent games used as a benchmark for multi-agent reinforcement learning.  ... 
doi:10.1007/978-3-540-75119-9_4 fatcat:34fgbkxbdfhbzfxmbn7n5thmrq

Verification for Machine Learning, Autonomy, and Neural Networks Survey [article]

Weiming Xiang and Patrick Musau and Ayana A. Wild and Diego Manzanas Lopez and Nathaniel Hamilton and Xiaodong Yang and Joel Rosenfeld and Taylor T. Johnson
2018 arXiv   pre-print
Autonomy in CPS is enabling by recent advances in artificial intelligence (AI) and machine learning (ML) through approaches such as deep neural networks (DNNs), embedded in so-called learning enabled components  ...  This survey presents an overview of verification techniques for autonomous systems, with a focus on safety-critical autonomous cyber-physical systems (CPS) and subcomponents thereof.  ...  Safe Reinforcement Learning Reinforcement Learning (RL) is a widely adopted frameworks in Artificial Intelligence for producing intelligent behavior in autonomous agents [71] .  ... 
arXiv:1810.01989v1 fatcat:a5ax66lsxbho3fuxuh55ypnm6m

Some agent theory for the semantic web

Leona F. Fass
2005 Software engineering notes  
We take the position that for any goal achievable on the Semantic Web, there will be a "best" system of Web-dwelling software agents to realize that goal, and that such a system may be discovered effectively  ...  Their applied research confirms that theory provides a good foundation for practice.  ...  We were invited to participate in the AAAI 2005 Fall Symposium on Agents and the Semantic Web, based on the initial draft of this paper.  ... 
doi:10.1145/1095430.1095442 fatcat:tl5ljryotneu3g5ppal4hnv4yi

An Adaptive Multi-agent Routing Algorithm Combining AntNet and Interconnected Learning Automata

Z. Farhadpour, M.R. Meybodi
2009 2009 International Conference on Advanced Computer Control  
The use of intelligent algorithms based on learning automata can be efficient for traffic control.  ...  In this paper, an adaptive multi-agent routing algorithm called LA-AntNet is proposed for both source and nonsource routing in communication networks.  ...  In this way agent's decisions are taken on the basis of a combination of a long-term learning process and an instantaneous heuristic prediction.  ... 
doi:10.1109/icacc.2009.117 fatcat:duc6tva7kfbyvdofb5ddnwpzna

Multi-agent modeling and simulation in the AI age

Wenhui Fan, Peiyu Chen, Daiming Shi, Xudong Guo, Li Kou
2021 Tsinghua Science and Technology  
Then we review the development status of the hybrid modeling and simulation combining multi-agent and system dynamics, the modeling and simulation of multi-agent reinforcement learning, and the modeling  ...  It also paves the way for further research on MAMS technology. Wenhui Fan et al.: Multi-Agent Modeling and Simulation in the AI Age 609 2 Multi-Agent Modeling and Simulation 2.  ...  of agents in multi-agent reinforcement learning. (3) The expansibility and knowledge transfer ability of multi-agent reinforcement learning are poor.  ... 
doi:10.26599/tst.2021.9010005 fatcat:em72oiw5mvgc7lp3pjmch3n2eq
« Previous Showing results 1 — 15 out of 1,997 results