Multi-agent reinforcement learning using function approximation

Download
082462.pdf
1999
Abul, Osman
Show full item record
60
views
0
downloads
https://hdl.handle.net/11511/2478
Graduate School of Natural and Applied Sciences, Thesis

Suggestions

Multi-agent reinforcement learning
Şenkul, Selçuk; Polat, Faruk; Department of Computer Engineering (1999)
Multi-agent reinforcement learning using roles
Çilden, Erkin; Polat, Faruk; Department of Computer Engineering (2001)
Multi-view video coding via dense depth estimation
Oezkalayci, Burak; Gedik, O. Serdar; Alatan, Abdullah Aydın (2007-05-09)
A geometry-based multi-view video coding (MVC) method is proposed. In order to utilize the spatial redundancies between multiple views, the scene geometry is estimated as dense depth maps. The dense depth estimation problem is modeled by using a Markov random field (MRF) and solved via the belief propagation algorithm. Relying on these depth maps of the scene, novel view estimates of the intermediate views of the multi-view set is obtained with a 3D warping algorithm, which also performs hole-filling in the...
Multi-aspect data fusion applied to electromagnetic target classification using enetic algorithm
Sayan, Gönül (2000-07-07)
Electromagnetic target detection and classification is an important problem relevant not only to military applications but also to civilian use. In the problem of a breast tumor detection and identification [1], for instance, the main concern is accuracy. In the case of the recognition of a military target such as an aircraft or a ship, on the other hand, speed of classification is as important as the accuracy of the decision as such a decision should be made within a fraction of a second. For the K-pulse t...
Multi-Aspect Data Fusion Applied to Electromagnetic Target Classification using Enetic Algorithm
Sayan, Gönül (Kluwer Academic Publishers, 2002-01-01)
Electromagnetic target detection and classification is an important problem relevant not only to military applications but also to civilian use. In the problem of a breast tumor detection and identification [1], for instance, the main concern is accuracy. In the case of the recognition of a military target such as an aircraft or a ship, on the other hand, speed of classification is as important as the accuracy of the decision as such a decision should be made within a fraction of a second. For...
Citation Formats
O. Abul, “Multi-agent reinforcement learning using function approximation,” Middle East Technical University, 1999.
METU IIS - Integrated Information Service open@metu.edu.tr