Sutton Barto Book: Reinforcement Learning: An Introduction Reinforcement Reinforcement Learning: Learning An Introduction Richard s. Sutton and andrew G, Barto MIT Press, Cambridge, MA, 1998 A Bradford book Endorsements Code Solutions Figures Errata Course Slides Hard s Sutton and Anew G, Harto This introductory textbook on reinforcement learning is targeted toward engineers and scientists in artificial intelligence, operations research, neural networks, and control systems, and we hope it will also be of interest to psychologists and neuroscientists If you would like to order a copy of the book, or if you are qualified instructor and would like to see an examination copy, please see the MIT Press home page for this book. Or you might be interested in the reviews at amazon. com. There is also a Japanese translation available The table of contents of the book is given below, with associated HTML. The hTML version has a number of presentation problems, and its text is slightly different from the real book, but it may be useful for some purposes Preface Part i: The problem 1 Introduction o 1.1 Reinforcement learning 1.2 Examples o 1 3 Elements of reinforcement learning o 1. 4 An Extended Example: Tic-Tac-Toe file: //Ibook/thebook. html (1 of 5)[28 08/382 03: 12: 45 3A
Sutton & Barto Book: Reinforcement Learning: An Introduction Reinforcement Learning: An Introduction Richard S. Sutton and Andrew G. Barto MIT Press, Cambridge, MA, 1998 A Bradford Book Endorsements Code Solutions Figures Errata Course Slides This introductory textbook on reinforcement learning is targeted toward engineers and scientists in artificial intelligence, operations research, neural networks, and control systems, and we hope it will also be of interest to psychologists and neuroscientists. If you would like to order a copy of the book, or if you are qualified instructor and would like to see an examination copy, please see the MIT Press home page for this book. Or you might be interested in the reviews at amazon.com. There is also a Japanese translation available. The table of contents of the book is given below, with associated HTML. The HTML version has a number of presentation problems, and its text is slightly different from the real book, but it may be useful for some purposes. ● Preface Part I: The Problem ● 1 Introduction ❍ 1.1 Reinforcement Learning ❍ 1.2 Examples ❍ 1.3 Elements of Reinforcement Learning ❍ 1.4 An Extended Example: Tic-Tac-Toe file:///C|/book/the-book.html (1 of 5) [28/08/1382 03:12:45 ﾕﾈﾍ]
Sutton Barto Book: Reinforcement Learning: An Introduction o 1.5 Summary o 1.6 History of Reinforcement Learning o 1.7 Bibliographical Remarks e2 Evaluative Feedback 2.1 An n-armed Bandit problem o 2. 2 Action-Value methods o 2.3 Softmax Action Selection o 2.4 Evaluation versus Instruction o 2. 5 Incremental Implementation o 2. 6 Tracking a Nonstationary Problem o 2. 7 Optimistic Initial values o 2. 8 Reinforcement Comparison o 2.9 Pursuit Methods 2.10 Associative searo o 2.11 Conclusion o 2. 12 Bibliographical and Historical Remarks 3 The Reinforcement Learning Problem o 3. 1 The Agent-Environment Interface o 3.2 Goals and Rewards o 3. 3 Returns o 3. 4 A Unified Notation for Episodic and Continual Tasks o 3. 5 The Markov Property o 3.6 Markov Decision Processes o 3.7 Value Functions o 3.8 Optimal Value Functions o 3.9 Optimality and Approximation 3.10 Summary o 3 11 Bibliographical and Historical Remarks Part Il: Elementary Methods 4 Dynamic Programming 4. 1 Policy Evaluation o 4.2 Policy Improvement o 4.3 Policy Iteration o 44 Value iteration e:∥/c|/ ookthe-book. htm(2of5)[2808∧38203:12:45卫
Sutton & Barto Book: Reinforcement Learning: An Introduction ❍ 1.5 Summary ❍ 1.6 History of Reinforcement Learning ❍ 1.7 Bibliographical Remarks ● 2 Evaluative Feedback ❍ 2.1 An n-armed Bandit Problem ❍ 2.2 Action-Value Methods ❍ 2.3 Softmax Action Selection ❍ 2.4 Evaluation versus Instruction ❍ 2.5 Incremental Implementation ❍ 2.6 Tracking a Nonstationary Problem ❍ 2.7 Optimistic Initial Values ❍ 2.8 Reinforcement Comparison ❍ 2.9 Pursuit Methods ❍ 2.10 Associative Search ❍ 2.11 Conclusion ❍ 2.12 Bibliographical and Historical Remarks ● 3 The Reinforcement Learning Problem ❍ 3.1 The Agent-Environment Interface ❍ 3.2 Goals and Rewards ❍ 3.3 Returns ❍ 3.4 A Unified Notation for Episodic and Continual Tasks ❍ 3.5 The Markov Property ❍ 3.6 Markov Decision Processes ❍ 3.7 Value Functions ❍ 3.8 Optimal Value Functions ❍ 3.9 Optimality and Approximation ❍ 3.10 Summary ❍ 3.11 Bibliographical and Historical Remarks Part II: Elementary Methods ● 4 Dynamic Programming ❍ 4.1 Policy Evaluation ❍ 4.2 Policy Improvement ❍ 4.3 Policy Iteration ❍ 4.4 Value Iteration file:///C|/book/the-book.html (2 of 5) [28/08/1382 03:12:45 ﾕﾈﾍ]
Sutton Barto Book: Reinforcement Learning: An Introduction o 4.5 Asynchronous Dynamic Programming o 4.6 Generalized Policy Iteration o 4.7 Efficiency of Dynamic Programming o 4.8 Summar o 4.9 Historical and Bibliographical Remarks 5 Monte Carlo Methods o 5. 1 Monte Carlo Policy Evaluation o 5.2 Monte Carlo Estimation of Action values o 5.3 Monte Carlo Control o 5.4 On-Policy Monte Carlo Control o 5.5 Evaluating One Policy While Following Another o 5.6 Off-Policy Monte Carlo Control o 5.7 Incremental Implementation o 5.8 Summary o 5.9 Historical and Bibliographical Remarks 6 Temporal Difference Learning o.1 TD Prediction o 6.2 Advantages of TD Prediction Methods o 6.3 Optimality of TD(O) o 6.4 Sarsa: On-Policy TD Control 6.5 Q-learning: Off-Policy TD Control o 6.6 Actor-Critic Methods (s o 6.7 R-Learning for Undiscounted Continual Tasks() o 6.8 Games, After States, and other Special Cases o 6.conclusions o 6.10 Historical and Bibliographical Remarks Part llle: a unified view ·7 Eligibility Traces 7. 1 n-step TD Prediction o 7.2 The Forward View of TDO. o 7.3 The Backward view of TDO o 7. 4 Equivalence of the Forward and Backward views o 7.5 Sarsa o76Q0 e:∥/c|/ ookthe-book. htm(3of5)[2808∧38203:12:45卫
Sutton & Barto Book: Reinforcement Learning: An Introduction ❍ 4.5 Asynchronous Dynamic Programming ❍ 4.6 Generalized Policy Iteration ❍ 4.7 Efficiency of Dynamic Programming ❍ 4.8 Summary ❍ 4.9 Historical and Bibliographical Remarks ● 5 Monte Carlo Methods ❍ 5.1 Monte Carlo Policy Evaluation ❍ 5.2 Monte Carlo Estimation of Action Values ❍ 5.3 Monte Carlo Control ❍ 5.4 On-Policy Monte Carlo Control ❍ 5.5 Evaluating One Policy While Following Another ❍ 5.6 Off-Policy Monte Carlo Control ❍ 5.7 Incremental Implementation ❍ 5.8 Summary ❍ 5.9 Historical and Bibliographical Remarks ● 6 Temporal Difference Learning ❍ 6.1 TD Prediction ❍ 6.2 Advantages of TD Prediction Methods ❍ 6.3 Optimality of TD(0) ❍ 6.4 Sarsa: On-Policy TD Control ❍ 6.5 Q-learning: Off-Policy TD Control ❍ 6.6 Actor-Critic Methods (*) ❍ 6.7 R-Learning for Undiscounted Continual Tasks (*) ❍ 6.8 Games, After States, and other Special Cases ❍ 6.9 Conclusions ❍ 6.10 Historical and Bibliographical Remarks Part III: A Unified View ● 7 Eligibility Traces ❍ 7.1 n-step TD Prediction ❍ 7.2 The Forward View of TD() ❍ 7.3 The Backward View of TD() ❍ 7.4 Equivalence of the Forward and Backward Views ❍ 7.5 Sarsa() ❍ 7.6 Q() file:///C|/book/the-book.html (3 of 5) [28/08/1382 03:12:45 ﾕﾈﾍ]
Sutton Barto Book: Reinforcement Learning: An Introduction o 7. 7 Eligibility Traces for Actor-Critic Methods o 7. 8 Replacing Traces o 7.9 Implementation Issues o 7.10 Variable o 7 11 Conclusions o 7 12 Bibliographical and Historical Remarks 8 Generalization and Function Approximation o 8.1 Value Prediction with Function Approximation o 8.2 Gradient-Descent Methods 08.3 Linear Methods 8.3 1 Coarse Co 8.3.2 Tile Coding 83. 3 Radial Basis Functions ■834 Kanerva Coding o 8.4 Control with Function Approximation o 8.5 Off-Policy Bootstrapping o 8.6 Should We Bootstrap? o 8/summary o 8.8 Bibliographical and Historical Remarks 9 Planning and Learning o 9. 1 Models and Planning o 9.2 Integrating Planning, Acting, and Learning o 9.3 When the Model is Wrong o 9.4 Prioritized Sweeping o 9.5 Full vs Sample Backups o 9.6 Trajectory Sampling 9.7 Heuristic Search 9. 8 Summary o 9.9 Historical and Bibliographical Remarks 10 Dimensions o 10.1 The Unified View o 10.2 Other frontier dimensions 11 Case Studies o.I TD-Gammon file: //Ibook /thebook. html (4 of 5)[28 08/382 03: 12: 45 3A
Sutton & Barto Book: Reinforcement Learning: An Introduction ❍ 7.7 Eligibility Traces for Actor-Critic Methods (*) ❍ 7.8 Replacing Traces ❍ 7.9 Implementation Issues ❍ 7.10 Variable (*) ❍ 7.11 Conclusions ❍ 7.12 Bibliographical and Historical Remarks ● 8 Generalization and Function Approximation ❍ 8.1 Value Prediction with Function Approximation ❍ 8.2 Gradient-Descent Methods ❍ 8.3 Linear Methods ■ 8.3.1 Coarse Coding ■ 8.3.2 Tile Coding ■ 8.3.3 Radial Basis Functions ■ 8.3.4 Kanerva Coding ❍ 8.4 Control with Function Approximation ❍ 8.5 Off-Policy Bootstrapping ❍ 8.6 Should We Bootstrap? ❍ 8.7 Summary ❍ 8.8 Bibliographical and Historical Remarks ● 9 Planning and Learning ❍ 9.1 Models and Planning ❍ 9.2 Integrating Planning, Acting, and Learning ❍ 9.3 When the Model is Wrong ❍ 9.4 Prioritized Sweeping ❍ 9.5 Full vs. Sample Backups ❍ 9.6 Trajectory Sampling ❍ 9.7 Heuristic Search ❍ 9.8 Summary ❍ 9.9 Historical and Bibliographical Remarks ● 10 Dimensions ❍ 10.1 The Unified View ❍ 10.2 Other Frontier Dimensions ● 11 Case Studies ❍ 11.1 TD-Gammon file:///C|/book/the-book.html (4 of 5) [28/08/1382 03:12:45 ﾕﾈﾍ]
Sutton Barto Book: Reinforcement Learning: An Introduction o 11.2 Samuel's Checkers Player o 11. 3 The Acrobot o 11.4 Elevator Dispatching o 11.5 Dynamic Channel Allocation o 11.6 Job-Shop Scheduling References Summary of Notation file://clbookthebook html (5 of 5)[28/08/382 03: 12: 45 1*]
Sutton & Barto Book: Reinforcement Learning: An Introduction ❍ 11.2 Samuel's Checkers Player ❍ 11.3 The Acrobot ❍ 11.4 Elevator Dispatching ❍ 11.5 Dynamic Channel Allocation ❍ 11.6 Job-Shop Scheduling ● References ● Summary of Notation file:///C|/book/the-book.html (5 of 5) [28/08/1382 03:12:45 ﾕﾈﾍ]