Multi-agent reinforcement learning using roles

Download
116240.pdf
2001
Çilden, Erkin
Show full item record
54
views
82
downloads
https://hdl.handle.net/11511/11495
Graduate School of Natural and Applied Sciences, Thesis

Suggestions

Multi-Mode Pushover Analysis with Generalized Force Vectors
Sucuoğlu, Haluk (2010-01-01)
Multi-Mode Pushover Analysis with Generalized Force Vectors
Sucuoğlu, Haluk (2009-07-01)
A generalized pushover analysis procedure is developed for estimating the inelastic seismic response of structures under earthquake ground excitations. The procedure comprises applying a generalized force vector to the structure in an incremental form with increasing amplitude until a prescribed seismic demand is attained. A generalized force vector is expressed as a combination of modal forces, and simulates the instantaneous force distribution acting on the system when a given interstory drift reaches its...
Multi-modal egocentric activity recognition using multi-kernel learning
Arabaci, Mehmet Ali; Ozkan, Fatih; Sürer, Elif; Jancovic, Peter; Temizel, Alptekin (2020-04-28)
Existing methods for egocentric activity recognition are mostly based on extracting motion characteristics from videos. On the other hand, ubiquity of wearable sensors allow acquisition of information from different sources. Although the increase in sensor diversity brings out the need for adaptive fusion, most of the studies use pre-determined weights for each source. In addition, there are a limited number of studies making use of optical, audio and wearable sensors. In this work, we propose a new framewo...
Multi-criteria decision making with interdependent criteria using prospect theory
Bozkurt, Ahmet; Karasakal, Esra; Department of Industrial Engineering (2007)
In this study, an integrated solution methodology for a general discrete multi-criteria decision making problem is developed based on the well-known outranking method Promethee II. While the methodology handles the existence of interdependency between the criteria, it can also incorporate the prospect theory in order to correctly reflect the decision behavior of the decision maker. A software is also developed for the application of the methodology and some applications are performed and presented.
Multiagent reinforcement learning using function approximation
Abul, O; Polat, Faruk; Alhajj, R (Institute of Electrical and Electronics Engineers (IEEE), 2000-11-01)
Learning in a partially observable and nonstationary environment is still one of the challenging problems In the area of multiagent (MA) learning. Reinforcement learning is a generic method that suits the needs of MA learning in many aspects. This paper presents two new multiagent based domain independent coordination mechanisms for reinforcement learning; multiple agents do not require explicit communication among themselves to learn coordinated behavior. The first coordination mechanism Is perceptual coor...
Citation Formats
E. Çilden, “Multi-agent reinforcement learning using roles,” Middle East Technical University, 2001.
METU IIS - Integrated Information Service open@metu.edu.tr