多主体强化学习协作策略研究【2025|PDF|Epub|mobi|kindle电子书版本百度云盘下载】

多主体强化学习协作策略研究PDF格式电子书版下载

注意：本站所有压缩包均有解压码： 点击下载压缩包解压工具

Chapter 1 Introduction1

1.1 Reinforcement Learning1

1.1.1 Generality of Reinforcement Learning1

1.1.2 Reinforcement Learning on Markov Decision Processes3

1.1.3 Integrating Reinforcement Learning into Agent Architecture5

1.2 Multiagent Reinforcement Learning7

1.2.1 Multiagent Systems7

1.2.2 Reinforcement Learning in Multiagent Systems11

1.2.3 Learning and Coordination in Multiagent Systems13

1.3 Ant System for Stochastic Combinatorial Optimization16

1.3.1 Ants Forage Behavior16

1.3.2 Ant Colony Optimization17

1.3.3 MAX-MIN Ant System19

1.4 Motivations and Consequences20

1.5 Book Summary22

Bibliography23

Chapter 2 Reinforcement Learning and Its Combination with Ant Colony System28

2.1 Introduction28

2.2 Investigation into Reinforcement Learning and Swarm Intelligence31

2.2.1 Temporal Differences Learning Method31

2.2.2 Active Exploration and Experience Replay in Reinforcement Learning32

2.2.3 Ant Colony System for Traveling Salesman Problem36

2.3 The Q-ACS Multiagent Learning Method39

2.3.1 The Q-ACS Learning Algorithm39

2.3.2 Some Properties of the Q-ACS Learning Method40

2.3.3 Relation with Ant-Q Learning Method41

2.4 Simulations and Results42

2.5 Conclusions43

Bibliography44

Chapter 3 Multiagent Learning Methods Based on Indirect Media Information Sharing47

3.1 Introduction47

3.2 The Multiagent Learning Method Considering Statistics Features49

3.2.1 Accelerated K-certainty Exploration49

3.2.2 The T-ACS Learning Algorithm50

3.3 The Heterogeneous Agents Learning52

3.3.1 The D-ACS Learning Algorithm52

3.3.2 Some Discussions about the D-ACS Learning Algorithm53

3.4 Comparisons with Related State-of-the-arts54

3.5 Simulations and Results57

3.5.1 Experimental Results on Hunter Game57

3.5.2 Experimental Results on Traveling Salesman Problem61

3.6 Conclusions66

Bibliography67

Chapter 4 Action Conversion Mechanism in Multiagent Reinforcement Learning71

4.1 Introduction71

4.2 Model-Based Reinforcement Learning72

4.2.1 Dyna-Q Architecture74

4.2.2 Prioritized Sweeping Method75

4.2.3 Minimax Search and Reinforcement Learning76

4.2.4 RTP-Q Learning77

4.3 The Q-ac Multiagent Reinforcement Learning78

4.3.1 Task Model79

4.3.2 Converting Action79

4.3.3 Multiagent Cooperation Methods80

4.3.4 Q-value Update82

4.3.5 The Q-ac Learning Algorithm83

4.3.6 Using Adversarial Action Instead of ε Probability Exploration84

4.4 Simulations and Results84

4.5 Conclusions87

Bibliography88

Chapter 5 Multiagent Learning Approaches Applied to Vehicle Routing Problems91

5.1 Introduction91

5.2 Related State-of-the-arts92

5.2.1 Some Heuristic Algorithms92

5.2.2 The Vehicle Routing Problem with Time Windows97

5.3 The Multiagent Learning Applied to CVRP and VRPTW99

5.4 Simulations and Results100

5.5 Conclusions103

Bibliography103

Chapter 6 Muitiagent learning Methods Applied to Multicast Routing Problems107

6.1 Introduction107

6.2 Multiagent Q-learning Applied to the Network Routing110

6.2.1 Investigation into Q-routing110

6.2.2 AntNet Investigation111

6.3 Some Multicast Routing in Mobile Ad Hoc Networks112

6.4 The Multiagent Q-learning in the Q-MAP Multicast Routing Method118

6.4.1 Overview of the Q-MAP Multicast Routing118

6.4.2 Join Query Packet,Join Reply Packet and Membership Maintenance119

6.4.3 Convergence Proof of Q-MAP Method122

6.5 Simulations and Results124

6.6 Conclusions128

Bibliography129

Chapter 7 Multiagent Reinforcement Learning for Supply Chain Management133

7.1 Introduction133

7.2 Related Issues of Supply Chain Management134

7.3 SCM Network Scheme with Multiagent Reinforcement Learning139

7.3.1 SCM with Multiagent139

7.3.2 The RL Agents in SCM Network140

7.4 Application of the Q-ACS Method to SCM142

7.4.1 The Application Model in SCM142

7.4.2 The Q-ACS Learning Applied to the SCM System144

7.5 Conclusion147

Bibliography147

Chapter 8 Multiagent Learning Applied in Supply Chain Ordering Management152

8.1 Introduction152

8.2 Supply Chain Management Model155

8.3 The Multiagent Learning Model for SC Ordering Management156

8.4 Simulations and Results159

8.5 Conclusions161

Bibliography162