Sökning: "exploration-exploitation."
Visar resultat 1 - 5 av 8 avhandlingar innehållade ordet exploration-exploitation..
1. Complexity in the 'Extended' Business Network : A Study of Business, Social, and Political Relationships in Smart City Solutions
Sammanfattning : In this thesis an 'extended' business network is investigated. The ‘extended’ view refers to the inclusion of socio-political actors in the firm’s business network. LÄS MER
2. Regret Minimization in Structured Reinforcement Learning
Sammanfattning : We consider a class of sequential decision making problems in the presence of uncertainty, which belongs to the field of Reinforcement Learning (RL). Specifically, we study discrete Markov decision Processes (MDPs) which model a decision maker or agent that interacts with a stochastic and dynamic environment and receives feedback from it in the form of a reward. LÄS MER
3. Knowledge processes and capabilities in project-based organizations
Sammanfattning : The beauty of projects lies in their ability to integrate different knowledge bases and expertise in novel ways. Projects, though, are temporary in nature and this has consequences for the organization that uses them as a business strategy to improve its efficiency. LÄS MER
4. Learning-Based Controller Design with Application to a Chiller Process
Sammanfattning : In this thesis, we present and study a few approaches for constructing controllers for uncertain systems, using a combination of classical control theory and modern machine learning methods. The thesis can be divided into two subtopics. The first, which is the focus of the first two papers, is dual control. LÄS MER
5. Reinforcement Learning and Optimal Adaptive Control for Structured Dynamical Systems
Sammanfattning : In this thesis, we study the related problems of reinforcement learning and optimal adaptive control, specialized to specific classes of stochastic and structured dynamical systems. By stochastic, we mean systems that are unknown to the decision maker and evolve according to some probabilistic law. LÄS MER