Sökning: "regret"

Visar resultat 11 - 15 av 46 avhandlingar innehållade ordet regret.

1. 11. Applications of Information Inequalities to Linear Systems : Adaptive Control and Security

   Författare :Ingvar Ziemann; Henrik Sandberg; Alexandre Proutiere; Nikolai Matni; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Stochastic Adaptive Control; Machine Learning; Fisher Information; Secure Control; Fundamental Limitations; Reinforcement Learning; Electrical Engineering; Elektro- och systemteknik;

   Sammanfattning : This thesis considers the application of information inequalities, Cramér-Rao type bounds, based on Fisher information, to linear systems. These tools are used to study the trade-offs between learning and performance in two application areas: adaptive control and control systems security. LÄS MER

3. 12. Inference and Online Learning in Structured Stochastic Systems

   Författare :Kaito Ariu; Alexandre Proutiere; Mikael Johansson; Wouter Koolen; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Electrical Engineering; Elektro- och systemteknik;

   Sammanfattning : This thesis contributes to the field of stochastic online learning problems, with a collection of six papers each addressing unique aspects of online learning and inference problems under specific structures. The first four papers focus on exploration and inference problems, uncovering fundamental information-theoretic limits and efficient algorithms under various structures. LÄS MER

4. 13. Age Differences in Experience and Regulation of Affect

   Författare :Pär Bjälkebring; Göteborgs universitet; []
   Nyckelord :SAMHÄLLSVETENSKAP; SOCIAL SCIENCES; Affect; Age;

   Sammanfattning : The overall aim of the thesis is to investigate differences in how younger and older adults view and control affect. Study I and Study II investigate how participants view their happiness and what factors influence their perception of happiness. In Study I we found weak negative association between age and happiness. LÄS MER

5. 14. Efficient Online Learning under Bandit Feedback

   Författare :Stefan Magureanu; Alexandre Proutiere; Odalric-Ambrym Maillard; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; multi-armed bandits; reinforcement learning; learning to rank; Electrical Engineering; Elektro- och systemteknik;

   Sammanfattning : In this thesis we address the multi-armed bandit (MAB) problem with stochastic rewards and correlated arms. Particularly, we investigate the case when the expected rewards are a Lipschitz function of the arm and extend these results to bandits with arbitrary structure that is known to the decision maker. LÄS MER

7. 15. Reinforcement Learning and Optimal Adaptive Control for Structured Dynamical Systems

   Författare :Damianos Tranos; Alexandre Proutiere; Pontus Giselsson; KTH; []
   Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Reinforcement Learning; Adaptive Control; Dynamical Systems; Control Theory; Control Engineering; Electrical Engineering; Elektro- och systemteknik;

   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