Loading...
Search for:
reinforcement-signal
0.007 seconds
Real-Time IDS using reinforcement learning
, Article 2008 2nd International Symposium on Intelligent Information Technology Application, IITA 2008, Shanghai, 21 December 2008 through 22 December 2008 ; Volume 2 , January , 2008 , Pages 593-597 ; 9780769534978 (ISBN) ; Bagheri Shouraki, S ; Hosein, K ; Mahdi, D ; Sharif University of Technology
2008
Abstract
In this paper we proposed a new real-time learning method. The engine of this method is a fuzzy-modeling technique which is called ink drop spread (IDS). IDS method has good convergence and is very simple and away from complex formula. The proposed method uses a reinforcement learning approach by an actor-critic system similar to Generalized Approximate Reasoning based Intelligent Control (GARIC) structure to adapt the IDS by delayed reinforcement signals. Our system uses Temporal Difference (TD) learning to model the behavior of useful actions of a control system. It is shown that the system can adapt itself, commencing with random actions. © 2008 IEEE
Cellular learning automata with external input and its applications in pattern recognition
, Article ICSCCW 2009 - 5th International Conference on Soft Computing, Computing with Words and Perceptions in System Analysis, Decision and Control ; 2009 ; 9781424434282 (ISBN) ; Beigy, H ; Sharif University of Technology
Abstract
Cellular learning automata (CLA) which has been introduced recently, is a combination of cellular automata (CA) and learning automata (LA). A CLA is a CA in which a LA is assigned to its every cell. The LA residing in each cell determines the state of the cell on basis of its action probability vector. Like CA, there is a local rule that CLA operates under it. In this paper we introduce a new model of CLA in which each cell gets an external input vector from the environment in addition to reinforcement signal, so this model can work in non-stationary environments. Then two applications of the new model on image segmentation and clustering are given, and the results show that the proposed...
Reinforcement learning based on active learning method
, Article Proceedings - 2008 2nd International Symposium on Intelligent Information Technology Application, IITA 2008, 21 December 2008 through 22 December 2008, Shanghai ; Volume 2 , 2008 , Pages 598-602 ; 9780769534978 (ISBN) ; Bagheri Shouraki, S ; Khasteh, H ; Kiaei, A. A ; Sharif University of Technology
2008
Abstract
In this paper, a new reinforcement learning approach is proposed which is based on a powerful concept named Active Learning Method (ALM) in modeling. ALM expresses any multi-input-single-output system as a fuzzy combination of some single-input-singleoutput systems. The proposed method is an actor-critic system similar to Generalized Approximate Reasoning based Intelligent Control (GARIC) structure to adapt the ALM by delayed reinforcement signals. Our system uses Temporal Difference (TD) learning to model the behavior of useful actions of a control system. The goodness of an action is modeled on Reward-Penalty-Plane. IDS planes will be updated according to this plane. It is shown that the...
Cellular Learning Automata and Its Applications in Pattern Recognition
, M.Sc. Thesis Sharif University of Technology ; Beigy, Hamid (Supervisor)
Abstract
Cellular learning automata (CLA) is a distributed computational model that is introduced recently. This model is combination of cellular automata (CA) and learning automata (LA) and is used in many applications such as image processing, channel assignment in cellular networks, VLSI placement, rumor diffusion and modeling of commerce networks, and obtained acceptable results in these applications. This model consists of computational units called cells and each cell has one or more learning automata. In each stage, each automaton chooses an action from its actions set and applies it to the environment. Each cell has some neighboring cells that constitute its local environment. The local rule...