Multi-Agent Coordination A Reinforcement Learning Approach.

Detalles Bibliográficos
Clasificación:Libro Electrónico
Autor principal: Sadhu, Arup Kumar
Otros Autores: Konar, Amit
Formato: Electrónico eBook
Idioma:Inglés
Publicado: Newark : John Wiley & Sons, Incorporated, 2020.
Colección:Wiley - IEEE Ser.
Temas:
Reinforcement learning.
Multiagent systems.
Apprentissage par renforcement (Intelligence artificielle)
Systèmes multiagents (Intelligence artificielle)
Multiagent systems
Reinforcement learning
Acceso en línea:Texto completo
Tabla de Contenidos:
  • Cover
  • Title Page
  • Copyright Page
  • Contents
  • Preface
  • Acknowledgments
  • Chapter 1 Introduction: Multi-agent Coordination by Reinforcement Learning and Evolutionary Algorithms
  • 1.1 Introduction
  • 1.2 Single Agent Planning
  • 1.2.1 Terminologies Used in Single Agent Planning
  • 1.2.2 Single Agent Search-Based Planning Algorithms
  • 1.2.2.1 Dijkstra's Algorithm
  • 1.2.2.2 A* (A-star) Algorithm
  • 1.2.2.3 D* (D-star) Algorithm
  • 1.2.2.4 Planning by STRIPS-Like Language
  • 1.2.3 Single Agent RL
  • 1.2.3.1 Multiarmed Bandit Problem
  • 1.2.3.2 DP and Bellman Equation
  • 1.2.3.3 Correlation Between RL and DP
  • 1.2.3.4 Single Agent Q-Learning
  • 1.2.3.5 Single Agent Planning Using Q-Learning
  • 1.3 Multi-agent Planning and Coordination
  • 1.3.1 Terminologies Related to Multi-agent Coordination
  • 1.3.2 Classification of MAS
  • 1.3.3 Game Theory for Multi-agent Coordination
  • 1.3.3.1 Nash Equilibrium
  • 1.3.3.2 Correlated Equilibrium
  • 1.3.3.3 Static Game Examples
  • 1.3.4 Correlation Among RL, DP, and GT
  • 1.3.5 Classification of MARL
  • 1.3.5.1 Cooperative MARL
  • 1.3.5.2 Competitive MARL
  • 1.3.5.3 Mixed MARL
  • 1.3.6 Coordination and Planning by MAQL
  • 1.3.7 Performance Analysis of MAQL and MAQL-Based Coordination
  • 1.4 Coordination by Optimization Algorithm
  • 1.4.1 PSO Algorithm
  • 1.4.2 Firefly Algorithm
  • 1.4.2.1 Initialization
  • 1.4.2.2 Attraction to Brighter Fireflies
  • 1.4.2.3 Movement of Fireflies
  • 1.4.3 Imperialist Competitive Algorithm
  • 1.4.3.1 Initialization
  • 1.4.3.2 Selection of Imperialists and Colonies
  • 1.4.3.3 Formation of Empires
  • 1.4.3.4 Assimilation of Colonies
  • 1.4.3.5 Revolution
  • 1.4.3.6 Imperialistic Competition
  • 1.4.4 Differential Evolution Algorithm
  • 1.4.4.1 Initialization
  • 1.4.4.2 Mutation
  • 1.4.4.3 Recombination
  • 1.4.4.4 Selection
  • 1.4.5 Off-line Optimization
  • 1.4.6 Performance Analysis of Optimization Algorithms
  • 1.4.6.1 Friedman Test
  • 1.4.6.2 Iman-Davenport Test
  • 1.5 Summary
  • References
  • Chapter 2 Improve Convergence Speed of Multi-Agent Q-Learning for Cooperative Task Planning
  • 2.1 Introduction
  • 2.2 Literature Review
  • 2.3 Preliminaries
  • 2.3.1 Single Agent Q-learning
  • 2.3.2 Multi-agent Q-learning
  • 2.4 Proposed MAQL
  • 2.4.1 Two Useful Properties
  • 2.5 Proposed FCMQL Algorithms and Their Convergence Analysis
  • 2.5.1 Proposed FCMQL Algorithms
  • 2.5.2 Convergence Analysis of the Proposed FCMQL Algorithms
  • 2.6 FCMQL-Based Cooperative Multi-agent Planning
  • 2.7 Experiments and Results
  • 2.8 Conclusions
  • 2.9 Summary
  • 2.A More Details on Experimental Results
  • 2.A.1 Additional Details of Experiment 2.1
  • 2.A.2 Additional Details of Experiment 2.2
  • 2.A.3 Additional Details of Experiment 2.4
  • References
  • Chapter 3 Consensus Q-Learning for Multi-agent Cooperative Planning
  • 3.1 Introduction
  • 3.2 Preliminaries
  • 3.2.1 Single Agent Q-Learning
  • 3.2.2 Equilibrium-Based Multi-agent Q-Learning
  • 3.3 Consensus

Ejemplares similares