Search for dissertations about: "Reward learning"
Showing result 21 - 25 of 66 swedish dissertations containing the words Reward learning.
-
21. Uncertainty, Worth, Identity : How Early Career Academics Navigate Evaluative Landscapes
Abstract : This dissertation explores the interplay between valuation and academic socialization, addressing the question: how do early career academics navigate evaluative landscapes? Having completed their doctoral education but yet to find stable employment, early career academics are generally viewed as the most vulnerable group of academic staff. Comparing how individuals within this group seek to demonstrate their worth in order to be recognized by others and advance in their careers, I try to make sense of their world. READ MORE
-
22. Reinforcement Learning Using Local Adaptive Models
Abstract : In this thesis, the theory of reinforcement learning is described and its relation to learning in biological systems is discussed. Some basic issues in reinforcement learning, the credit assignment problem and perceptual aliasing, are considered. The methods of temporal difference are described. READ MORE
-
23. Learning Methods for Antenna Tilt Optimization
Abstract : The increasing complexity of modern mobile networks poses unprecedented challenges to Mobile Network Operators (MNOs). MNOs need to utilize network resources optimally to satisfy the growing demand of network users in a reliable manner. READ MORE
-
24. Dopamine and the affective-cognitive gradient in the human striatum studied with multimodal brain imaging
Abstract : Both dopamine and the dopamine rich brain area, striatum, have been linked to behaviors related to incentives, motor action, and associative processing. Most of the cortex sends projections to the striatum, these connections have been described as a gradient organization representing a repertoire of functional behaviors. READ MORE
-
25. On the optimal stopping time of learning
Abstract : The goal of this thesis is to study the economics of computational learning. Attention is also paid to applications of computational learning models, especially Valiant's so-called `probably approximately correctly' (PAC) learning model, in econometric situations. READ MORE