Autonomous Agents and Multi-Agent Systems : Explorations in Learning, Self-Organization and Adaptive Computation.
Title:
Autonomous Agents and Multi-Agent Systems : Explorations in Learning, Self-Organization and Adaptive Computation.
Author:
Liu, Jiming.
ISBN:
9789812811844
Personal Author:
Physical Description:
1 online resource (302 pages)
Contents:
Contents -- Preface -- Acknowledgements -- Chapter 1 Introduction -- 1.1 What is an Agent? -- 1.2 Basic Questions and Fundamental Issues -- 1.3 Learning -- 1.3.1 Learning in Natural and Artificial Systems -- 1.3.2 Agent Learning Techniques -- 1.4 Neural Agents -- 1.4.1 Self-Organizing Maps (SOM) -- 1.4.2 SOM Applications -- 1.5 Evolutionary Agents -- 1.6 Learning in Cooperative Agents -- 1.7 Computational Architectures -- 1.7.1 Subsumption Architecture -- 1.7.2 Action Selection -- 1.7.3 Motif Architecture -- 1.8 Agent Behavioral Learning -- 1.8.1 What is the Behavior of a Learning Agent? -- 1.8.2 What is Behavioral Learning? -- Chapter 2 Behavioral Modeling, Planning, and Learning -- 2.1 Manipulation Behaviors -- 2.2 Modeling and Planning Manipulation Behaviors -- 2.2.1 State-Oriented Representation -- 2.2.2 State-Transition Function (Φ) -- 2.2.3 Behavioral Planning Based on Action Schemata -- 2.3 Manipulation Behavioral Learning -- 2.3.1 Automatic Induction of State Transitions -- 2.3.2 Empirical Sample Generation -- 2.4 Summary -- 2.5 Other Modeling, Planning, and Learning Methods -- 2.5.1 Artificial Potential Fields (APF) -- 2.5.2 Artificial Neural Networks (ANN) -- 2.5.3 Similarities and Differences between APF and ANN -- 2.5.4 APF Meets ANN -- 2.5.5 Summary -- 2.6 Bibliographical and Historical Remarks -- 2.6.1 Assembly Operation Planning -- 2.6.2 AI Planning -- 2.6.3 Manipulation Behavioral Planning -- Chapter 3 Synthetic Autonomy -- 3.1 Synthetic Autonomy Based on Behavioral Self-Organization -- 3.2 Behavioral Self-Organization -- 3.2.1 Overview -- 3.2.2 The Athlete Agent -- 3.3 Summary -- 3.4 Bibliographical and Historical Remarks -- 3.4.1 Animation of Articulated Figures -- 3.4.2 Lifelike Behavior -- 3.4.3 Emergent Behavior -- Chapter 4 Dynamics of Distributed Computation -- 4.1 Definitions.
4.2 Overview of the Approach -- 4.2.1 Local Stimuli to Agents -- 4.2.2 Reactive Behavior of Distributed Agents -- 4.3 Dynamics of Agent-Based Distributed Search -- 4.3.1 Dynamic Systems Models -- 4.3.2 Agents with Different Dynamic Behaviors -- 4.3.3 Summary of Agent-Based Distributed Computation -- 4.4 Remarks -- 4.4.1 Dynamic Systems Modeling -- 4.4.2 Agent Semi-Autonomy -- 4.4.3 Characteristics of the Agent-Based Approach -- 4.4.4 The Goal-Attainability of Agents -- 4.5 Summary -- 4.5.1 Open Problems -- 4.5.2 Extensions -- 4.6 Bibliographical and Historical Remarks -- Chapter 5 Self-Organized Autonomy in Multi-Agent Systems -- 5.1 Collective Vision and Motion -- 5.2 Self-Organized Vision for Image Feature Detection and Tracking -- 5.2.1 Overview of Self-Organized Vision -- 5.2.2 A Two-Dimensional Lattice Environment -- 5.2.3 Local Stimuli in a Two-Dimensional Lattice -- 5.2.4 Self-Organizing Behaviors -- 5.2.5 The Reproduce-and-Diffuse (R-D) Algorithm -- 5.2.6 Examples -- 5.3 Self-Organized Motion in Group Robots -- 5.3.1 The Task of Group Navigation and Homing -- 5.3.2 Overview of the Multi-Agent System -- 5.3.3 Local Memory-Based Behavioral Selection and Global Performance-Based Behavioral Learning -- 5.3.4 Dynamics of Different Agent Groups -- 5.3.5 Examples -- 5.3.6 Remarks -- 5.4 Summary -- 5.5 Bibliographical and Historical Remarks -- 5.5.1 Cellular Automata -- 5.5.2 Learning in Group Robots -- Chapter 6 Autonomy-Oriented Computation -- 6.1 Terminology -- 6.2 The Adaptive Self-Organizing Behavior-Based Agents -- 6.2.1 Overview -- 6.2.2 The Adaptive Self-Organizing Behaviors of Agents -- 6.2.3 Agent Convergence -- 6.3 The General Characteristics of Agents -- 6.4 The Adaptive Reproduce-and-Diffuse (aR-D) Algorithm -- 6.5 Examples -- 6.6 Computational Costs.
6.7 Comparisons with Conventional Segmentation Approaches -- 6.8 Effects of Behavioral Characteristics on Agent-Based Search -- 6.9 Parameters Affecting Agent Computation -- 6.10 Dynamics of Autonomous Agents -- 6.10.1 Understanding Agent Dynamics -- 6.10.2 A Continuous Model of Agent Dynamics -- 6.10.3 Deriving a Model of Agent Dynamics -- 6.11 Balance between Learning and Evolution -- 6.12 Summary -- 6.13 Bibliographical and Historical Remarks -- 6.13.1 Feature Extraction -- 6.13.2 Segmentation -- Chapter 7 Dynamics and Complexity of Autonomy-Oriented Computation -- 7.1 Decentralized Agent Behaviors -- 7.2 Goal-Attainability -- 7.2.1 Goal-Attainability in E where dimE = 1 -- 7.2.2 Goal-Attainability in E where dimE = 2 -- 7.2.3 Effects of Behavioral Parameters on Goal-Attainability -- 7.3 Population Dynamics -- 7.3.1 Population Dynamics in E where dimE = 1 -- 7.3.2 Population Dynamics in E where dimE = 2 -- 7.4 Examples -- 7.4.1 Goal-Attaining Optimality -- 7.5 Complexity of Autonomy-Oriented Computation -- 7.5.1 Background -- 7.5.2 The Complexity of an Environment -- 7.5.3 Examples -- 7.6 Summary -- 7.7 Bibliographical and Historical Remarks -- Bibliography -- Index.
Abstract:
An autonomous agent is a computational system that acquires sensory data from its environment and decides by itself how to relate the external stimulus to its behaviors in order to attain certain goals. Responding to different stimuli received from its task environment, the agent may select and exhibit different behavioral patterns. The behavioral patterns may be carefully predefined or dynamically acquired by the agent based on some learning and adaptation mechanism(s). In order to achieve structural flexibility, reliability through redundancy, adaptability, and reconfigurability in real-world tasks, some researchers have started to address the issue of multiagent cooperation. Broadly speaking, the power of autonomous agents lies in their ability to deal with unpredictable, dynamically changing environments. Agent-based systems are becoming one of the most important computer technologies, holding out many promises for solving real-world problems. The aims of this book are to provide a guided tour to the pioneering work and the major technical issues in agent research, and to give an in-depth discussion on the computational mechanisms for behavioral engineering in autonomous agents. Through a systematic examination, the book attempts to provide the general design principles for building autonomous agents and the analytical tools for modeling the emerged behavioral properties of a multiagent system. Contents: Behavioral Modeling, Planning, and Learning; Synthetic Autonomy; Dynamics of Distributed Computation; Self-Organized Autonomy in Multi-Agent Systems; Autonomy-Oriented Computation; Dynamics and Complexity of Autonomy-Oriented Computation. Readership: Undergraduate and graduate students in computer science and most engineering disciplines, as well as computer scientists, engineers, researchers and practitioners in the field of machine
intelligence.
Local Note:
Electronic reproduction. Ann Arbor, Michigan : ProQuest Ebook Central, 2017. Available via World Wide Web. Access may be limited to ProQuest Ebook Central affiliated libraries.
Genre:
Electronic Access:
Click to View