Networks of Learning Automata

Thathachar, M. A. L.; Sastry, P. S.

doi:10.1007/978-1-4419-9052-5

Cited by 159 publications

(91 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The proof follows similar lines as in [42]. However, we extend the result to a more general setting where the underlying N-person stochastic game is a weighted potential game.…”

Section: Appendix Proof Of Theoremmentioning

confidence: 60%

“…; Q, denotes the probability that the lth user transmits with a rate of r Next, we formulate an identical interest game where the players are the jILj source nodes and the common objective function is the overall network utility, i.e., the summation of the utility functions. In addition, for each source node, a team of learning automata [42] is constructed. At each time step, every source node picks the data rates on its own paths according to the probability vectors, which are determined by the weighting vectors.…”

Section: Decentralized Algorithmic Solution With the Learning Automatmentioning

confidence: 99%

“…However, we extend the result to a more general setting where the underlying N-person stochastic game is a weighted potential game. Therefore, the proof in [42] can be viewed as a special case. Define V as the potential function of the game.…”

Section: Appendix Proof Of Theoremmentioning

confidence: 99%

See 2 more Smart Citations

Stochastic Traffic Engineering in Multihop Cognitive Wireless Mesh Networks

Song

Zhang

Fang

2010

IEEE Trans. on Mobile Comput.

View full text Add to dashboard Cite

Abstract-In this work, the stochastic traffic engineering problem in multihop cognitive wireless mesh networks is addressed. The challenges induced by the random behaviors of the primary users are investigated in a stochastic network utility maximization framework. For the convex stochastic traffic engineering problem, we propose a fully distributed algorithmic solution which provably converges to the global optimum with probability one. We next extend our framework to the cognitive wireless mesh networks with nonconvex utility functions, where a decentralized algorithmic solution, based on learning automata techniques, is proposed. We show that the decentralized solution converges to the global optimum solution asymptotically.

show abstract

“…The proof follows similar lines as in [42]. However, we extend the result to a more general setting where the underlying N-person stochastic game is a weighted potential game.…”

Section: Appendix Proof Of Theoremmentioning

confidence: 60%

Section: Decentralized Algorithmic Solution With the Learning Automatmentioning

confidence: 99%

See 1 more Smart Citation

Stochastic Traffic Engineering in Multihop Cognitive Wireless Mesh Networks

Song

Zhang

Fang

2010

IEEE Trans. on Mobile Comput.

View full text Add to dashboard Cite

show abstract

“…In these equations, a and b are reward and penalty parameters respectively. For more information about learning automata the reader may refer to [77][78][79].…”

Section: Learning Automatamentioning

confidence: 99%

Deployment of a mobile wireless sensor network with k-coverage constraint: a cellular learning automata approach

Esnaashari

Meybodi

2012

Wireless Netw

View full text Add to dashboard Cite

Deployment of a wireless sensor network is a challenging problem, especially when the environment of the network does not allow either of the random deployment or the exact placement of sensor nodes. If sensor nodes are mobile, then one approach to overcome this problem is to first deploy sensor nodes randomly in some initial region within the area of the network, and then let the sensor nodes to move around and cooperatively and gradually increase the covered section of the area. Recently, a cellular learning automata-based deployment strategy, called CLA-DS, is introduced in literature which follows this approach and is robust against inaccuracies which may occur in the measurements of sensor positions or in the movements of sensor nodes. Despite its advantages, this deployment strategy covers every point within the area of the network with only one sensor node, which is not enough for applications with k-coverage requirement. In this paper, we extend CLA-DS so that it can address the k-coverage requirement. This extension, referred to as CLA-EDS, is also able to address k-coverage requirement with different values of k in different regions of the network area. Experimental results have shown that the proposed deployment strategy, in addition to the advantages it inherits from CLA-DS, outperforms existing algorithms such as DSSA, IDCA, and DSLE in covering the network area, especially when required degree of coverage differs in different regions of the network.

show abstract

“…Additionally we have implemented another exploration policy so called stochastic learning automata [11]. It updates the MCS selection probability vector so that the probability to choose the MCS with the best empirical performance is the highest and converges to 1 as we see more and more positive feedback that the MCS is the best one.…”

Section: Exploration Vs Exploitationmentioning

confidence: 99%

Reinforcement Learning for Link Adaptation in MIMO-OFDM Wireless Systems

Yun

Caramanis

2010

2010 IEEE Global Telecommunications Conference GLOBECOM 2010

View full text Add to dashboard Cite

Abstract-Machine learning algorithms have recently attracted much interest for effective link adaptation due to their flexibility and ability to capture more environmental effects implicitly than classical adaptation algorithms. However, past applications are limited to rather simple configurations such as identifying channel condition or link adaptation in fixed or slowly varying channels. Recently, more sophisticated approaches using offline supervised learning have been proposed for link adaptation in complex configurations such as MIMO-OFDM. However, their time complexity and offline training phase hamper their real-world applicability. Approaches using online learning have shown good throughput performance, but the high memory requirement makes them inefficient or even impractical. In this paper, we propose a new effective online learning algorithm for link adaptation. Our computations show that the algorithm performs comparably to the existing online learning approaches, but ours requires minimal storage and time, which makes it more practical. Moreover it adapts to the change of channel distribution quickly.

show abstract

Networks of Learning Automata

Cited by 159 publications

References 0 publications

Stochastic Traffic Engineering in Multihop Cognitive Wireless Mesh Networks

Stochastic Traffic Engineering in Multihop Cognitive Wireless Mesh Networks

Deployment of a mobile wireless sensor network with k-coverage constraint: a cellular learning automata approach

Reinforcement Learning for Link Adaptation in MIMO-OFDM Wireless Systems

Contact Info

Product

Resources

About