Decentralized Supervisory Control of Discrete Event Systems Based on Reinforcement Learning(<Special Section>Concurrent/Hybrid Systems : Theory and Applications)
スポンサーリンク
概要
- 論文の詳細を見る
A supervisor proposed by Ramadge and Wonham controls a discrete event system (DES) so as to satisfy logical control specifications. However a precise description of both the specifications and the DES is needed for the control. This paper proposes a synthesis method of the supervisor for decentralized DESs based on reinforcement learning. In decentralized DESs, several local supervisors exist and control the DES jointly. Costs for disabling and occurrence of events as well as control specifications are considered. By using reinforcement learning, the proposed method is applicable under imprecise specifications and uncertain environment.
- 一般社団法人電子情報通信学会の論文
- 2005-11-01
著者
-
Ushio Toshimitsu
Graduate School Of Engineering Science Osaka University
-
Ushio Toshimitsu
Graduate School Of Engineering Science At Osaka University
-
YAMASAKI Tatsushi
School of Science and Technology, Kwansei Gakuin University
-
Yamasaki Tatsushi
School Of Science And Technology Kwansei Gakuin University
関連論文
- Adaptive Fair Resource Allocation for Energy and QoS Trade-Off Management
- Adaptive Fair Sharing Control in Real-Time Systems Using Nonlinear Elastic Task Models(Nonlinear Problems)
- Synthesis of Nonautonomous Systems with Specified Limit Cycles(Oscillation, Dynamics and Chaos,Nonlinear Theory and its Applications)
- Analysis of Automation Surprises in Human-Machine Systems with Time Information(Selected Papers from the 18th Workshop on Circuits and Systems in Karuizawa)
- Special Section on Nonlinear Theory and its Applications
- Sampled-Data Event Control of Hybrid Systems for Control Specifications Given by Predicate
- Scheduling of Periodic Tasks on a Dynamically Reconfigurable Device Using Timed Discrete Event Systems(Concurrent Systems,Concurrent/Hybrid Systems: Theory and Applications)
- Optimal Configuration for Multiversion Real-Time Systems Using Slack Based Schedulability
- Automatic Generation of User Manuals without Automation Surprises for Human-Machine Systems Modeled by Discrete Event Systems
- Synthesis of Hybrid Systems with Limit Cycles Satisfying Piecewise Smooth Constraint Equations(Selected Papers from the 16th Workshop on Circuits and Systems in Karuizawa)
- PID Congestion Control in ATM with Propagation Delay
- Control-Invariance of Sampled-Data Hybrid Systems with Clocked Events and Jitters(Selected Papers from the 19th Workshop on Circuits and Systems in Karuizawa)
- On-Line Control of Discrete Event Systems with a Maximally Controllable and Observable Sublanguage
- Controlling Chaos in a Hogg-Huberman Model of a Manufacturing System
- Decentralized Supervisory Control of Discrete Event Systems Based on Reinforcement Learning(Concurrent/Hybrid Systems : Theory and Applications)
- Co-scheduling of Communication and Control of Multi-Hop Control Networks
- An Application of Game Automaton to Quantitative Supervisory Control
- An Application of Game Automaton to Quantitative Supervisory Control
- A-12-2 An Approximate Method for Solving Optimal Control Problems of MLD systems