Multi-agent reinforcement learning

Şenkul, Selçuk


Multi-agent reinforcement learning using function approximation
Abul, Osman; Polat, Faruk; Department of Computer Engineering (1999)
Multi-subject brain decoding using deep learning techniques
Velioğlu, Burak; Yarman Vural, Fatoş Tunay; Ertekin Bolelli, Şeyda; Department of Computer Engineering (2016)
In this study, a new method is proposed for analyzing and classifying images obtained by functional magnetic resonance imaging (fMRI) from multiple subjects. Considering the multi level structure of the brain and success of deep learning architectures on extracting hierarchical representations from raw data, these architectures are used in this thesis. Initially, the S500 data set collected in the scope of Human Connectome Project (HCP) is used to train formed deep neural networks in an unsupervised fashion...
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...
Multiobjective hub location problem
Barutçuoğlu, Aras; Köksalan, Murat; Department of Industrial Engineering (2009)
In this study, we propose a two-phase solution approach for approximating the efficient frontier of a bicriteria hub location problem. We develop an evolutionary algorithm to locate the hubs on the network as the first phase. In the second phase, we develop a bounding procedure based on dominance relations and using the determined bounds, we solve the allocation subproblem for each located hub set. The two-phase approach is tested on the Australian Post data set and it is observed that our approach approxim...
Multi-objective feasibility enhanced particle swarm optimization
Hasanoglu, Mehmet Sinan; Dölen, Melik (Informa UK Limited, 2018-12-02)
This article introduces a new method entitled multi-objective feasibility enhanced partical swarm optimization (MOFEPSO), to handle highly-constrained multi-objective optimization problems. MOFEPSO, which is based on the particle swarm optimization technique, employs repositories of non-dominated and feasible positions (or solutions) to guide feasible particle flight. Unlike its counterparts, MOFEPSO does not require any feasible solutions in the initialized swarm. Additionally, objective functions are not ...
Citation Formats
S. Şenkul, “Multi-agent reinforcement learning,” Middle East Technical University, 1999.