策略前展策略迭代与分布式强化学习(英文版)/信息技术学科与电

本书主要内容：第1章为 动态规划原理；第2章为策 略前展与策略改进；第3章 为专用策略前展算法；第4 章为值和策略的学习；第5 章为无限时间分布式和多智 能体算法。 横空出世的围棋软件 AlphaZero算法对本书有很 大影响。本书内容同样基于 策略迭代、值网络和策略网 络的神经网络近似表示、并 行与分布式计算和前瞻最小 化约简技术的核心框架构建 ，并对算法的适用范围做了 拓展。本书的特色在于给出 了分布式计算和多智能体系 统框架下的强化学习策略改 进计算的效率提升技术，建 立了一步策略改进策略前展 方法同控制系统中广泛使用 的模型预测控制（MPC）设 计方法之间的联系，并描述 了策略前展方法在复杂离散 和组合优化问题方面的应用 。 通过阅读本书，读者可 以了解强化学习中的策略迭 代，特别是策略前展方法在 分布式和多智能体框架下的 最新进展和应用。本书可用 作人工智能或系统与控制科 学等相关专业的高年级本科 生或研究生的教材，也适合 开展相关研究工作的专业技 术人员作为参考书。

Dimitri P. Bertsekas,德梅萃 P.博塞克斯（Dimitri P. Bertseka）,美国MIT终身教授，美国国家工程院院士，清华大学复杂与网络化系统研究中心客座教授。电气工程与计算机科学领域国际知名作者，著有《非线性规划》《网络优化》《动态规划》《凸优化》《强化学习与最优控制》等十几本畅销教材和专著。

1 Exact and Approximate Dynamic Programming Principles 1.1 AlphaZero, Off-Line Training, and On-Line Play 1.2 Deterministic Dynamic Programming 1.2.1 Finite Horizon Problem Formulation 1.2.2 The Dynamic Programming Algorithm 1.2.3 Approximation in Value Space 1.3 Stochastic Dynamic Programming 1.3.1 Finite Horizon Problems 1.3.2 Approximation in Value Space for Stochastic DP 1.3.3 Infinite Horizon Problems-An Overview 1.3.4 Infinite Horizon-Approximation in Value Space 1.3.5 Infinite Horizon-Policy Iteration, Rollout, andNewton's Method 1.4 Examples, Variations, and Simplifications 1.4.1 A Few Words About Modeling 1.4.2 Problems with a Termination State 1.4.3 State Augmentation, Time Delays, Forecasts, and Uncontrollable State Components 1.4.4 Partial State Information and Belief States 1.4.5 Multiagent Problems and Multiagent Rollout 1.4.6 Problems with Unknown Parameters-AdaptiveControl 1.4.7 Adaptive Control by Rollout and On-LineReplanning 1.5 Reinforcement Learning and Optimal Control-SomeTerminology 1.6 Notes and Sources 2 General Principles of Approximation in Value Space 2.1 Approximation in Value and Policy Space 2.1.1 Approximation in Value Space-One-Step and Multistep Lookahead 2.1.2 Approximation in Policy Space 2.1.3 Combined Approximation in Value and Policy Space 2.2 Approaches for Value Space Approximation 2.2.1 Off-Line and On-Line Implementations 2.2.2 Model-Based and Model-Free Implementations 2.2.3 Methods for Cost-to-Go Approximation 2.2.4 Methods for Expediting the Lookahead Minimization 2.3 Deterministic Rollout and the Policy Improvement Principle 2.3.1 On-Line Rollout for Deterministic Discrete Optimization 2.3.2 Using Multiple Base Heuristics-Parallel Rollout 2.3.3 The Simplified Rollout Algorithm 2.3.4 The Fortified Rollout Algorithm 2.3.5 Rollout with Multistep Lookahead 2.3.6 Rollout with an Expert 2.3.7 Rollout with Small Stage Costs and Long Horizon-Continuous-Time Rollout 2.4 Stochastic Rollout and Monte Carlo Tree Search 2.4.1 Simulation-Based Implementation of the Rollout Algorithm 2.4.2 Monte Carlo Tree Search 2.4.3 Randomized Policy Improvement by Monte Carlo Tree Search 2.4.4 The Effect of Errors in Rollout-Variance Reduction 2.4.5 Rollout Parallelization 2.5 Rollout for Infinite-Spaces Problems-Optimization Heuristics 2.5.1 Rollout for Infinite-Spaces Deterministic Problems 2.5.2 Rollout Based on Stochastic Programming 2.6 Notes and Sources