Generalized Models of Sequential Decision-Making under Uncertainty

Sequential decision-making under uncertainty is an important branch of artificial intelligence research with a plethora of real-life applications. In this thesis, we generalize two fundamental properties of the decision-making process. First, we show that the theory on planning methods for finite spaces can be extended to infinite but countable...

Applications of Quantum Computation and Algorithmic Information: for Causal Modeling in Genomics and Reinforcement Learning

Efforts to realize a sufficiently large controllable quantum processor are actively being pursued globally. These quantum devices are programmed by specifying the manipulation of quantum information via quantum algorithms. This doctoral research provides an application perspective to the design requirements of a quantum accelerator architecture....

Balancing and redispatch: the next stepping stones in European electricity market integration: Improving the market design and the efficiency of the procurement of balancing and redispatch services

Balancing and redispatch are essential services for the security and stability of the electricity network. Balancing refers to continuously maintaining a balance between supply and demand through activating flexible resources. Redispatch refers to changing the dispatch of generators to remedy network congestion. The need for flexibility...

Online Model Learning Algorithms for Actor-Critic Control

Classical control theory requires a model to be derived for a system, before any control design can take place. This can be a hard, time-consuming process if the system is complex. Moreover, there is no way of escaping modelling errors. As an alternative approach, there is the possibility of having the system learn a controller by itself while...

Reinforcement Learning on autonomous humanoid robots

Service robots have the potential to be of great value in households, health care and other labor intensive environments. However, these environments are typically unique, not very structured and frequently changing, which makes it difficult to make service robots robust and versatile through manual programming. Having robots learn to solve...

Ant Colony Optimization for Control

The very basis of this thesis is the collective behavior of ants in colonies. Ants are an excellent example of how rather simple behavior on a local level can lead to complex behavior on a global level that is beneficial for the individuals. The key in the self-organization of ants is communication through pheromones. When an ant forages for...