Multi-Agent Machine Learning : A Reinforcement Approach.
Title:
Multi-Agent Machine Learning : A Reinforcement Approach.
Author:
Schwartz, H. M.
ISBN:
9781118884478
Personal Author:
Edition:
1st ed.
Physical Description:
1 online resource (458 pages)
Contents:
Cover -- Table of Contents -- Title -- Copyright -- Preface -- References -- Chapter 1: A Brief Review of Supervised Learning -- 1.1 Least Squares Estimates -- 1.2 Recursive Least Squares -- 1.3 Least Mean Squares -- 1.4 Stochastic Approximation -- References -- Chapter 2: Single-Agent Reinforcement Learning -- 2.1 Introduction -- 2.2 n-Armed Bandit Problem -- 2.3 The Learning Structure -- 2.4 The Value Function -- 2.5 The Optimal Value Functions -- 2.6 Markov Decision Processes -- 2.7 Learning Value Functions -- 2.8 Policy Iteration -- 2.9 Temporal Difference Learning -- 2.10 TD Learning of the State-Action Function -- 2.11 Q-Learning -- 2.12 Eligibility Traces -- References -- Chapter 3: Learning in Two-Player Matrix Games -- 3.1 Matrix Games -- 3.2 Nash Equilibria in Two-Player Matrix Games -- 3.3 Linear Programming in Two-Player Zero-Sum Matrix Games -- 3.4 The Learning Algorithms -- 3.5 Gradient Ascent Algorithm -- 3.6 WoLF-IGA Algorithm -- 3.7 Policy Hill Climbing (PHC) -- 3.8 WoLF-PHC Algorithm -- 3.9 Decentralized Learning in Matrix Games -- 3.10 Learning Automata -- 3.11 Linear Reward-Inaction Algorithm -- 3.12 Linear Reward-Penalty Algorithm -- 3.13 The Lagging Anchor Algorithm -- 3.14 L R-I Lagging Anchor Algorithm -- References -- Chapter 4: Learning in Multiplayer Stochastic Games -- 4.1 Introduction -- 4.2 Multiplayer Stochastic Games -- 4.3 Minimax-Q Algorithm -- 4.4 Nash Q-Learning -- 4.5 The Simplex Algorithm -- 4.6 The Lemke-Howson Algorithm -- 4.7 Nash-Q Implementation -- 4.8 Friend-or-Foe Q-Learning -- 4.9 Infinite Gradient Ascent -- 4.10 Policy Hill Climbing -- 4.11 WoLF-PHC Algorithm -- 4.12 Guarding a Territory Problem in a Grid World -- 4.13 Extension of L R-I Lagging Anchor Algorithm to Stochastic Games -- 4.14 The Exponential Moving-Average Q-Learning (EMA Q-Learning) Algorithm.
4.15 Simulation and Results Comparing EMA Q-Learning to Other Methods -- References -- Chapter 5: Differential Games -- 5.1 Introduction -- 5.2 A Brief Tutorial on Fuzzy Systems -- 5.3 Fuzzy Q-Learning -- 5.4 Fuzzy Actor-Critic Learning -- 5.5 Homicidal Chauffeur Differential Game -- 5.6 Fuzzy Controller Structure -- 5.7 Q(λ)-Learning Fuzzy Inference System -- 5.8 Simulation Results for the Homicidal Chauffeur -- 5.9 Learning in the Evader-Pursuer Game with Two Cars -- 5.10 Simulation of the Game of Two Cars -- 5.11 Differential Game of Guarding a Territory -- 5.12 Reward Shaping in the Differential Game of Guarding a Territory -- 5.13 Simulation Results -- References -- Chapter 6: Swarm Intelligence and the Evolution of Personality Traits -- 6.1 Introduction -- 6.2 The Evolution of Swarm Intelligence -- 6.3 Representation of the Environment -- 6.4 Swarm-Based Robotics in Terms of Personalities -- 6.5 Evolution of Personality Traits -- 6.6 Simulation Framework -- 6.7 A Zero-Sum Game Example -- 6.8 Implementation for Next Sections -- 6.9 Robots Leaving a Room -- 6.10 Tracking a Target -- 6.11 Conclusion -- References -- Index -- End User License Agreement.
Abstract:
The book begins with a chapter on traditional methods of supervised learning, covering recursive least squares learning, mean square error methods, and stochastic approximation. Chapter 2 covers single agent reinforcement learning. Topics include learning value functions, Markov games, and TD learning with eligibility traces. Chapter 3 discusses two player games including two player matrix games with both pure and mixed strategies. Numerous algorithms and examples are presented. Chapter 4 covers learning in multi-player games, stochastic games, and Markov games, focusing on learning multi-player grid games-two player grid games, Q-learning, and Nash Q-learning. Chapter 5 discusses differential games, including multi player differential games, actor critique structure, adaptive fuzzy control and fuzzy interference systems, the evader pursuit game, and the defending a territory games. Chapter 6 discusses new ideas on learning within robotic swarms and the innovative idea of the evolution of personality traits. Framework for understanding a variety of methods and approaches in multi-agent machine learning. Discusses methods of reinforcement learning such as a number of forms of multi-agent Q-learning Applicable to research professors and graduate students studying electrical and computer engineering, computer science, and mechanical and aerospace engineering.
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:
Added Author:
Electronic Access:
Click to View