(Downloads - 0)
For more info about our services contact : help@bestpfe.com
Table of contents
1 Introduction
1.1 Motivation and Objective
1.2 Reinforcement Learning
1.3 Overview and Contributions
I Literature Review
2 Reinforcement Learning
2.1 Markov Decision Processes
2.2 Dynamic Programming
2.2.1 Policy Iteration
2.2.2 Value Iteration
2.2.3 Interaction between Policy Evaluation and Policy Improvement
2.3 Temporal-Dierence Methods
2.4 Function Approximation Methods
2.5 Exploration
2.6 Model-Based and Model-Free Methods
2.7 Priority-Based Value Iteration
2.8 Non-Stationary Environment
II Applications
3 Model-Free and Model-Based Methods
3.1 Introduction
3.2 Learning without Models
3.2.1 Background and Related Work
3.2.2 Q-learning for Taxi Routing
3.2.3 Performance Evaluation
3.2.4 Demonstration Scenario
3.3 Learning Models
3.3.1 Background: Factored MDP
3.3.2 Related work
3.3.3 Algorithm for Structure Learning
3.3.4 Experiments
3.4 Discussion and Future Research
3.5 Conclusion
4 Focused Crawling
4.1 Introduction
4.2 Background
4.3 Focused Crawling and Reinforcement Learning
4.3.1 Markov Decision Processes (MDPs) in Crawling
4.3.2 MDPs with Prioritizing Updates
4.3.3 Linear Function Approximation with Prioritizing Updates
4.4 Experimental Results
4.5 Related Work
4.6 Future Work
4.7 Conclusion
5 Inuence Maximization
5.1 Introduction
5.2 Background
5.3 Topic-Based Inuence Maximization Algorithm for Unknown Graphs
5.3.1 Problem Statement and our Method
5.3.2 Modeling and Algorithm
5.4 Related Work
5.5 Future Work
5.6 Conclusion
6 Conclusion
6.1 Future Work
6.2 Conclusion
Bibliography
Appendices
