{"product_id":"multi-agent-machine-learning-a-reinforcement-approach-hardback-9781118362082","title":"Multi-Agent Machine Learning; A Reinforcement Approach (Hardback) 9781118362082","description":"\u003cfont face=\"Georgia\"\u003e\r\n\u003cp\u003e\u003cfont size=\"6\"\u003eMulti-Agent Machine Learning\u003c\/font\u003e\u003cbr\u003e\r\n\u003cfont size=\"5\"\u003eA Reinforcement Approach\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\r\n\r\n\r\n\u003cp\u003e\u003cfont size=\"4\"\u003eH. M. Schwartz (Author)\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003e9781118362082, Wiley\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003eHardback, published 26 September 2014\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003e256 pages\u003cbr\u003e23.9 x 15.8 x 1.8 cm, 0.476 kg\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\r\n\r\n\u003cp align=\"justify\"\u003e\u003cem\u003e\u003cfont size=\"3\"\u003e\u003cp\u003e“This is an interesting book both as research reference as well as teaching material for Master and PhD students.”  (\u003ci\u003eZentralblatt MATH\u003c\/i\u003e, 1 April 2015)\u003c\/p\u003e \u003cp\u003e \u003c\/p\u003e \u003cp\u003e.\u003c\/p\u003e\u003c\/font\u003e\u003c\/em\u003e\u003c\/p\u003e\r\n\r\n\u003cp align=\"justify\"\u003e\u003cstrong\u003e\u003cfont size=\"3\"\u003e\u003cp\u003eThe 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.\u003cbr\u003e \u003cbr\u003e • Framework for understanding a variety of methods and approaches in multi-agent machine learning.\u003cbr\u003e \u003cbr\u003e • Discusses methods of reinforcement learning such as a number of forms of multi-agent Q-learning\u003cbr\u003e \u003cbr\u003e • Applicable to research professors and graduate students studying electrical and computer engineering, computer science, and mechanical and aerospace engineering\u003c\/p\u003e\u003c\/font\u003e\u003c\/strong\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003e\u003cp\u003e\u003ci\u003ePreface ix\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 1 A Brief Review of Supervised Learning 1\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e1.1 Least Squares Estimates 1\u003c\/p\u003e \u003cp\u003e1.2 Recursive Least Squares 5\u003c\/p\u003e \u003cp\u003e1.3 Least Mean Squares 6\u003c\/p\u003e \u003cp\u003e1.4 Stochastic Approximation 10\u003c\/p\u003e \u003cp\u003eReferences 11\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 2 Single-Agent Reinforcement Learning 12\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e2.1 Introduction 12\u003c\/p\u003e \u003cp\u003e2.2 n-Armed Bandit Problem 13\u003c\/p\u003e \u003cp\u003e2.3 The Learning Structure 15\u003c\/p\u003e \u003cp\u003e2.4 The Value Function 17\u003c\/p\u003e \u003cp\u003e2.5 The Optimal Value Functions 18\u003c\/p\u003e \u003cp\u003e2.5.1 The Grid World Example 20\u003c\/p\u003e \u003cp\u003e2.6 Markov Decision Processes 23\u003c\/p\u003e \u003cp\u003e2.7 Learning Value Functions 25\u003c\/p\u003e \u003cp\u003e2.8 Policy Iteration 26\u003c\/p\u003e \u003cp\u003e2.9 Temporal Difference Learning 28\u003c\/p\u003e \u003cp\u003e2.10 TD Learning of the State-Action Function 30\u003c\/p\u003e \u003cp\u003e2.11 Q-Learning 32\u003c\/p\u003e \u003cp\u003e2.12 Eligibility Traces 33\u003c\/p\u003e \u003cp\u003eReferences 37\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 3 Learning in Two-Player Matrix Games 38\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e3.1 Matrix Games 38\u003c\/p\u003e \u003cp\u003e3.2 Nash Equilibria in Two-Player Matrix Games 42\u003c\/p\u003e \u003cp\u003e3.3 Linear Programming in Two-Player Zero-Sum Matrix Games 43\u003c\/p\u003e \u003cp\u003e3.4 The Learning Algorithms 47\u003c\/p\u003e \u003cp\u003e3.5 Gradient Ascent Algorithm 47\u003c\/p\u003e \u003cp\u003e3.6 WoLF-IGA Algorithm 51\u003c\/p\u003e \u003cp\u003e3.7 Policy Hill Climbing (PHC) 52\u003c\/p\u003e \u003cp\u003e3.8 WoLF-PHC Algorithm 54\u003c\/p\u003e \u003cp\u003e3.9 Decentralized Learning in Matrix Games 57\u003c\/p\u003e \u003cp\u003e3.10 Learning Automata 59\u003c\/p\u003e \u003cp\u003e3.11 Linear Reward–Inaction Algorithm 59\u003c\/p\u003e \u003cp\u003e3.12 Linear Reward–Penalty Algorithm 60\u003c\/p\u003e \u003cp\u003e3.13 The Lagging Anchor Algorithm 60\u003c\/p\u003e \u003cp\u003e3.14 LR−I Lagging Anchor Algorithm 62\u003c\/p\u003e \u003cp\u003e3.14.1 Simulation 68\u003c\/p\u003e \u003cp\u003eReferences 70\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 4 Learning in Multiplayer Stochastic Games 73\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e4.1 Introduction 73\u003c\/p\u003e \u003cp\u003e4.2 Multiplayer Stochastic Games 75\u003c\/p\u003e \u003cp\u003e4.3 Minimax-Q Algorithm 79\u003c\/p\u003e \u003cp\u003e4.3.1 2 ×2 Grid Game 80\u003c\/p\u003e \u003cp\u003e4.4 Nash Q-Learning 87\u003c\/p\u003e \u003cp\u003e4.4.1 The Learning Process 95\u003c\/p\u003e \u003cp\u003e4.5 The Simplex Algorithm 96\u003c\/p\u003e \u003cp\u003e4.6 The Lemke–Howson Algorithm 100\u003c\/p\u003e \u003cp\u003e4.7 Nash-Q Implementation 107\u003c\/p\u003e \u003cp\u003e4.8 Friend-or-Foe Q-Learning 111\u003c\/p\u003e \u003cp\u003e4.9 Infinite Gradient Ascent 112\u003c\/p\u003e \u003cp\u003e4.10 Policy Hill Climbing 114\u003c\/p\u003e \u003cp\u003e4.11 WoLF-PHC Algorithm 114\u003c\/p\u003e \u003cp\u003e4.12 Guarding a Territory Problem in a Grid World 117\u003c\/p\u003e \u003cp\u003e4.12.1 Simulation and Results 119\u003c\/p\u003e \u003cp\u003e4.13 Extension of LR−I Lagging Anchor Algorithm to Stochastic Games 125\u003c\/p\u003e \u003cp\u003e4.14 The Exponential Moving-Average Q-Learning (EMA Q-Learning) Algorithm 128\u003c\/p\u003e \u003cp\u003e4.15 Simulation and Results Comparing EMA Q-Learning to Other Methods 131\u003c\/p\u003e \u003cp\u003e4.15.1 Matrix Games 131\u003c\/p\u003e \u003cp\u003e4.15.2 Stochastic Games 134\u003c\/p\u003e \u003cp\u003eReferences 141\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 5 Differential Games 144\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e5.1 Introduction 144\u003c\/p\u003e \u003cp\u003e5.2 A Brief Tutorial on Fuzzy Systems 146\u003c\/p\u003e \u003cp\u003e5.2.1 Fuzzy Sets and Fuzzy Rules 146\u003c\/p\u003e \u003cp\u003e5.2.2 Fuzzy Inference Engine 148\u003c\/p\u003e \u003cp\u003e5.2.3 Fuzzifier and Defuzzifier 151\u003c\/p\u003e \u003cp\u003e5.2.4 Fuzzy Systems and Examples 152\u003c\/p\u003e \u003cp\u003e5.3 Fuzzy Q-Learning 155\u003c\/p\u003e \u003cp\u003e5.4 Fuzzy Actor–Critic Learning 159\u003c\/p\u003e \u003cp\u003e5.5 Homicidal Chauffeur Differential Game 162\u003c\/p\u003e \u003cp\u003e5.6 Fuzzy Controller Structure 165\u003c\/p\u003e \u003cp\u003e5.7 Q()-Learning Fuzzy Inference System 166\u003c\/p\u003e \u003cp\u003e5.8 Simulation Results for the Homicidal Chauffeur 171\u003c\/p\u003e \u003cp\u003e5.9 Learning in the Evader–Pursuer Game with Two Cars 174\u003c\/p\u003e \u003cp\u003e5.10 Simulation of the Game of Two Cars 177\u003c\/p\u003e \u003cp\u003e5.11 Differential Game of Guarding a Territory 180\u003c\/p\u003e \u003cp\u003e5.12 Reward Shaping in the Differential Game of Guarding a Territory 184\u003c\/p\u003e \u003cp\u003e5.13 Simulation Results 185\u003c\/p\u003e \u003cp\u003e5.13.1 One Defender Versus One Invader 185\u003c\/p\u003e \u003cp\u003e5.13.2 Two Defenders Versus One Invader 191\u003c\/p\u003e \u003cp\u003eReferences 197\u003c\/p\u003e \u003cp\u003e\u003cb\u003eChapter 6 Swarm Intelligence and the Evolution of Personality Traits 200\u003c\/b\u003e\u003c\/p\u003e \u003cp\u003e6.1 Introduction 200\u003c\/p\u003e \u003cp\u003e6.2 The Evolution of Swarm Intelligence 200\u003c\/p\u003e \u003cp\u003e6.3 Representation of the Environment 201\u003c\/p\u003e \u003cp\u003e6.4 Swarm-Based Robotics in Terms of Personalities 203\u003c\/p\u003e \u003cp\u003e6.5 Evolution of Personality Traits 206\u003c\/p\u003e \u003cp\u003e6.6 Simulation Framework 207\u003c\/p\u003e \u003cp\u003e6.7 A Zero-Sum Game Example 208\u003c\/p\u003e \u003cp\u003e6.7.1 Convergence 208\u003c\/p\u003e \u003cp\u003e6.7.2 Simulation Results 214\u003c\/p\u003e \u003cp\u003e6.8 Implementation for Next Sections 216\u003c\/p\u003e \u003cp\u003e6.9 Robots Leaving a Room 218\u003c\/p\u003e \u003cp\u003e6.10 Tracking a Target 221\u003c\/p\u003e \u003cp\u003e6.11 Conclusion 232\u003c\/p\u003e \u003cp\u003e\u003ci\u003eReferences 233\u003c\/i\u003e\u003c\/p\u003e \u003cp\u003e\u003ci\u003eIndex 237\u003c\/i\u003e\u003c\/p\u003e\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\u003cp\u003e\u003cfont size=\"3\"\u003eSubject Areas: Electronics \u0026amp; communications engineering [\u003ca title=\"See our other books on Electronics \u0026amp; communications engineering\" href=\"https:\/\/freshlyprintedbooks.co.uk\/search?q=%22Electronics%20\u0026amp;%20communications%20engineering%20%5BTJ%5D%22\"\u003eTJ\u003c\/a\u003e]\u003c\/font\u003e\u003c\/p\u003e\r\n\r\n\r\n\u003c\/font\u003e","brand":"Wiley","offers":[{"title":"Brand New","offer_id":52417770586392,"sku":"9781118362082","price":85.89,"currency_code":"GBP","in_stock":true}],"thumbnail_url":"\/\/cdn.shopify.com\/s\/files\/1\/0730\/2037\/5320\/files\/9781118362082.jpg?v=1784507813","url":"https:\/\/freshlyprintedbooks.co.uk\/products\/multi-agent-machine-learning-a-reinforcement-approach-hardback-9781118362082","provider":"Freshly Printed Books","version":"1.0","type":"link"}