The purpose of this thesis was to compare the performance of three different imitation learning algorithms with human experts, with limited expert time. The central question was, ”How should one implement imitation learning in a simulated car racing environment, using human experts, to achieve the best performance when access to the experts is limited?”. We limited the work to only consider the three algorithms Behavior Cloning, DAGGER, and HG-DAGGER and limited the implementation to the car racing simulator TORCS. The agents consisted of the same type of feedforward neural network that utilized sensor data provided by TORCS. Through comparison in the performance of the different algorithms on a different amount of expert time, we can conclude that HGDAGGER performed the best. In this case, performance is regarded as a distance covered given set time. Its performance also seemed to scale well with more expert time, which the others did not. This result confirmed previously published results when comparing these algorithms. / Målet med detta examensarbete var att jämföra prestandan av tre olika algoritmer inom området imitationinlärning med mänskliga experter, där experttiden är begränsad. Arbetets frågeställning var, ”Hur ska man implementera imitationsinlärning i en bilsimulator, för att få bäst prestanda, med mänskliga experter där experttiden är begränsad?”. Vi begränsade arbetet till att endast omfatta de tre algoritmerna, Behavior Cloning, DAGGER och HG-DAGGER, och begränsade implementationsmiljön till bilsimulatorn TORCS. Alla agenterna bestod av samma sorts feedforward neuralt nätverk som använde sig av sensordata från TROCS. Genom jämförelse i prestanda på olika mängder experttid kan vi dra slutsatsen att HG-DAGGER gav bäst resultat. I detta fall motsvarar prestanda körsträcka, givet en viss tid. Dess prestanda verkar även utvecklas väl med ytterligare experttid, vilket de övriga inte gjorde. Detta resultat bekräftar tidigare publicerade resultat om jämförelse av de tre olika algoritmerna.

The field of machine learning currently draws massive attention due to ad- vancements and successful applications announced in the last few years. One of these applications is self-driving vehicles. A machine learning model can learn to drive through behavior cloning. Behavior cloning uses an expert’s behavioral traces as training data. However, the model’s steering predictions influence the succeeding input to the model and thus the model’s input data will vary depending on earlier predictions. Eventually the vehicle may de- viate from the expert’s behavioral traces and fail due to encountering data it has not been trained on. This is the problem of sequential predictions. DAG- GER and its improvement SafeDAGGER are algorithms that enable training models in the sequential prediction domain. Both algorithms iteratively col- lect new data, aggregate new and old data and retrain models on all data to avoid catastrophically forgetting previous knowledge. The aggregation of data leads to problems with increasing model training times, memory requirements and requires that previous data is maintained forever. This thesis’s purpose is investigate whether or not SafeDAGGER can be improved with continual learning to create a more scalable and flexible algorithm. This thesis presents an improved algorithm called EWC-SD that uses the continual learning algo- rithm EWC to protect a model’s previous knowledge and thereby only train on new data. Training only on new data allows EWC-SD to have lower training times, memory requirements and avoid storing old data forever compared to the original SafeDAGGER. The different algorithms are evaluated in the con- text of self-driving vehicles on three tracks in the VBS3 simulator. The results show EWC-SD when trained on new data only does not reach the performance of SafeDAGGER. Adding a rehearsal buffer containing only 23 training exam- ples to EWC-SD allows it to outperform SafeDAGGER by reaching the same performance in half as many iterations. The conclusion is that EWC-SD with rehearsal solves the problems of increasing model training times, memory re- quirements and requiring access to all previous data imposed by data aggre- gation. / Fältet för maskininlärning drar för närvarande massiv uppmärksamhet på grund av framsteg och framgångsrika applikationer som meddelats under de senaste åren. En av dessa applikationer är självkörande fordon. En maskininlärningsmodell kan lära sig att köra ett fordon genom beteendekloning. Beteendekloning använder en experts beteendespår som träningsdata. En modells styrförutsägelser påverkar emellertid efterföljande indata till modellen och således varierar modellens indata utifrån tidigare förutsägelser. Så småningom kan fordonet avvika från expertens beteendespår och misslyckas på grund av att modellen stöter på indata som den inte har tränats på. Det här är problemet med sekventiella förutsägelser. DAGGER och dess förbättring SafeDAGGER är algoritmer som möjliggör att träna modeller i domänen sekventiella förutsägelser. Båda algoritmerna samlar iterativt nya data, aggregerar nya och gamla data och tränar om modeller på alla data för att undvika att katastrofalt glömma tidigare kunskaper. Aggregeringen av data leder till problem med ökande träningstider, ökande minneskrav och kräver att man behåller åtkomst till all tidigare data för alltid. Avhandlingens syfte är att undersöka om SafeDAGGER kan förbättras med stegvis inlärning för att skapa en mer skalbar och flexibel algoritm. Avhandlingen presenterar en förbättrad algoritm som heter EWC-SD, som använder stegvis inlärningsalgoritmen EWC för att skydda en modells tidigare kunskaper och därigenom enbart träna på nya data. Att endast träna på nya data gör det möjligt för EWC-SD att ha lägre träningstider, ökande minneskrav och undvika att lagra gamla data för evigt jämfört med den ursprungliga SafeDAGGER. De olika algoritmerna utvärderas i kontexten självkörande fordon på tre banor i VBS3-simulatorn. Resultaten visar att EWC-SD tränad enbart på nya data inte uppnår prestanda likvärdig SafeDAGGER. Ifall en lägger till en repeteringsbuffert som innehåller enbart 23 träningsexemplar till EWC-SD kan den överträffa SafeDAGGER genom att uppnå likvärdig prestanda i hälften så många iterationer. Slutsatsen är att EWC-SD med repeteringsbuffert löser problemen med ökande träningstider, ökande minneskrav samt kravet att alla tidigare data ständigt är tillgängliga som påtvingas av dataaggregering.

(in English): This thesis aims at collecting, cataloguing and analysing bronze objects from the area of the East Aegean-West Anatolian Interface in the second millennium B.C. Based on closer typological assessment and comparanda, the question of eventual local specific production along the Interface, different from the Aegea or Eastern Mediterranean, is being investigated here. From up to 217 collected items, indeed many types of bronzes, especially swords, razors and spearheads indeed show a set of specific features. Also, the characteristic of bronze metals differs in Lower Interface with stronger minoan-mycenaen influnce from items in Upper Interface which seems to be following more anatolian features.

The goal of this thesis is to create a mobile application for Android that will offer management for reservations of training lessons. There are two user roles in the application. The first one is coach who can offer his lessons to other users. Users then can book this lesson right from the application. Coach can also manage all of his lessons and see his reservations in calendar. The second type of user is an athlete who can search for training lessons by name or place distance and then he can book them. The name of the application is Fittyy and it complies with Material Design rules. It uses advanced technologies like Android Jetpack to store local data, implement MVVM model or process server requests in the background. Communication between coach and athlete was implemented using CMS system made by Dactyl Group s.r.o.

Creating realistic models of human fighter pilot behavior is made possible with recent deep learning techniques. However, these techniques are often highly dependent on large datasets, often unavailable in many settings, or expensive to produce. Transfer learning is an active research field where the idea is to leverage the knowledge gained from studying a problem for which large amounts of training data are more readily available, when considering a different, related problem. The related problem is called the target task and the initial problem is called the source task. Given a successful transfer scenario, a smaller amount of data, or less training, can be required to reach high quality results on the target task. The first part of this thesis focuses on the development of a fighter pilot model using behavior cloning, a method for reducing an imitation learning problem to standard supervised learning. The resulting model, called a policy, is capable of imitating a human pilot controlling a fighter jet in the military combat simulator Virtual BattleSpace 3. In this simulator, the forces acting on the aircraft can be modelled using one of several flight dynamic models (FDMs). In the second part, the efficiency of transfer learning is measured. This is done by replacing the built-in FDM to one with a significant variation in the input response, and subsequently train two policies on successive amount of data. One policy was trained using only the latter FDM, whereas the other policy exploits the gained knowledge from the first part of the thesis, using a technique called fine-tuning. The results indicate that a model already capable of handling one FDM, adapts to a different FDM with less data compared to a previously untrained policy. / Realistiska modeller av mänskligt pilotbeteende kan potentiellt skapas med djupinlärningstekniker. För detta krävs ofta stora datamängder som för många tillämpningar saknas, eller är dyra att ta fram. Överföringsinlärning är ett aktivt forskningsfält där grundidén är att utnyttja redan inlärd kunskap från ett problem där stora mängder träningsdata finns tillgängligt, vid undersökning av ett relaterat problem. Vid lyckad överföringinlärning behövs en mindre mängd data, eller mindre träning, för att uppnå ett önskvärt resultat på denna måluppgift. Första delen av detta examensarbete handlar om utvecklingen av en pilotmodell med hjälp av beteendekloning, en metod som reducerar imitationsinlärning till vanlig övervakad inlärning. Den resulterande pilotmodellen klarar av att imitera en mänsklig pilot som styr ett stridsflygplan i den militära simulatormiljön Virtual BattleSpace 3, där krafterna som verkar på flygplanet modelleras med en enkel inbyggd flygdynamiksmodell. I den andra delen av arbetet utvärderas överföringsförmågan mellan olika flygdynamiksmodeller. Detta gjordes genom att ersätta den inbyggda dynamiken till en dynamik som modellerar ett annat flygplan och som svarar på styrsignaler på ett vida olikartat sätt. Sedan tränades två stridspilotmodeller successivt på ökad mängd data. Den ena pilotmodellen tränas endast med den ena dynamiken varvid den andra pilotmodellen utnyttjar det redan inlärda beteendet från första delen av arbetet, med hjälp av en teknik som kallas finjustering. Resultaten visar att en pilotmodell som redan lärt sig att flyga med en specifik flygdynamik har lättare att lära sig en ny dynamik, jämfört med en pilotmodell som inte förtränats.

Optimal control for multicopters is difficult in part due to the low processing power available, and the instability inherent to multicopters. Deep imitation learning is a method for approximating an expert control policy with a neural network, and has the potential of improving control for multicopters. We investigate the performance and reliability of deep imitation learning with trajectory optimization as the expert policy by first defining a dynamics model for multicopters and applying a trajectory optimization algorithm to it. Our investigation shows that network architecture plays an important role in the characteristics of both the learning process and the resulting control policy, and that in particular trajectory optimization can be leveraged to improve convergence times for imitation learning. Finally, we identify some limitations and future areas of study and development for the technology. / Optimal kontroll för multikoptrar är ett svårt problem delvis på grund av den vanligtvis låga processorkraft som styrdatorn har, samt att multikoptrar är synnerligen instabila system. Djup imitationsinlärning är en metod där en beräkningstung expert approximeras med ett neuralt nätverk, och gör det därigenom möjligt att köra dessa tunga experter som realtidskontroll för multikoptrar. I detta arbete undersöks prestandan och pålitligheten hos djup imitationsinlärning med banoptimering som expert genom att först definiera en dynamisk modell för multikoptrar, sedan applicera en välkänd banoptimeringsmetod på denna modell, och till sist approximera denna expert med imitationsinlärning. Vår undersökning visar att nätverksarkitekturen spelar en avgörande roll för karakteristiken hos både inlärningsprocessens konvergenstid, såväl som den resulterande kontrollpolicyn, och att särskilt banoptimering kan nyttjas för att förbättra konvergenstiden hos imitationsinlärningen. Till sist påpekar vi några begränsningar hos metoden och identifierar särskilt intressanta områden för framtida studier.

The purpose of this essay is to analyze the ideological development of the former communist parties and the contemporary left-wing socialist parties of the Nordic countries. It is aimed at the two decades that have passed since the collaps of the Berlin wall and the parties at hand are; the Norwegian Sosialistisk Venstre, the Danish Socialistisk Folkeparti, the Swedish Vänsterpartiet and the Finnish Vasemmistoliitto. Since the 1960´s these parties have undergone major ideological changes with reference to a widening of their political agenda to an inclusion of democratic ideals as well as the new ideologies of feminism and ecologism. Thus reforming them into modern left-wing socialist parties at different times. The main hypothesis is formulated from the idea that there must be a connection between the startingpoint of reformation and the degree of modernism/traditionalism they show today. Furthermore, the study intends to determine how much they have changed and if there are any common features in the development. The method used consists of a quantitative approach with a minor qualitative streak and the material includes the four parties principalprograms from 1990 until today. In the quantative part I chose to count an amount of value-related words with connection to the four categories of socialism, feminism, ecologism and the democratic ideal. With the ideological refinement of Ball and Dagger as a frame of reference i chose a big amount of words, in which case the qualitative approach constituted as a failsafe in order to determine every words accuracy. The research shows that my original hypothesis is only partly correct. The degree of modernization seems to be depending on whereas the party was founded before or after the collapse of the Berlin wall. The fact that the three Scandinavian parties all show a positive modernization in comparison to their Finnish counterpart supports that. The study also reveals that the Finnish party, without consideration of modernism/traditionalism, changes the most during the period and the Danish party changes the least. The main feature of the Scandinavian parties is the decline of socialistic ideas in comparison to their Finnish equivalent.

Algebraic Quantum Field Theory (AQFT) is a mathematically rigorous framework that was developed to model the interaction of quantum mechanics and relativity. In AQFT, quantum mechanics is modelled by C*-algebras of observables and relativity is usually modelled in Minkowski space. In this thesis we will consider a generalization of AQFT which was inspired by the work of Abramsky and Coecke on abstract quantum mechanics [1, 2]. In their work, Abramsky and Coecke develop a categorical framework that captures many of the essential features of finite-dimensional quantum mechanics. In our setting we develop a categorified version of AQFT, which we call premonoidal C*-quantum field theory, and in the process we establish many analogues of classical results from AQFT. Along the way we also exhibit a number of new concepts, such as a von Neumann category, and prove several properties they possess. We also establish some results that could lead to proving a premonoidal version of the classical Doplicher-Roberts theorem, and conjecture a possible solution to constructing a fibre-functor. Lastly we look at two variations on AQFT in which a causal order on double cones in Minkowski space is considered.

Algebraic Quantum Field Theory (AQFT) is a mathematically rigorous framework that was developed to model the interaction of quantum mechanics and relativity. In AQFT, quantum mechanics is modelled by C*-algebras of observables and relativity is usually modelled in Minkowski space. In this thesis we will consider a generalization of AQFT which was inspired by the work of Abramsky and Coecke on abstract quantum mechanics [1, 2]. In their work, Abramsky and Coecke develop a categorical framework that captures many of the essential features of finite-dimensional quantum mechanics. In our setting we develop a categorified version of AQFT, which we call premonoidal C*-quantum field theory, and in the process we establish many analogues of classical results from AQFT. Along the way we also exhibit a number of new concepts, such as a von Neumann category, and prove several properties they possess. We also establish some results that could lead to proving a premonoidal version of the classical Doplicher-Roberts theorem, and conjecture a possible solution to constructing a fibre-functor. Lastly we look at two variations on AQFT in which a causal order on double cones in Minkowski space is considered.

Algebraic Quantum Field Theory (AQFT) is a mathematically rigorous framework that was developed to model the interaction of quantum mechanics and relativity. In AQFT, quantum mechanics is modelled by C*-algebras of observables and relativity is usually modelled in Minkowski space. In this thesis we will consider a generalization of AQFT which was inspired by the work of Abramsky and Coecke on abstract quantum mechanics [1, 2]. In their work, Abramsky and Coecke develop a categorical framework that captures many of the essential features of finite-dimensional quantum mechanics. In our setting we develop a categorified version of AQFT, which we call premonoidal C*-quantum field theory, and in the process we establish many analogues of classical results from AQFT. Along the way we also exhibit a number of new concepts, such as a von Neumann category, and prove several properties they possess. We also establish some results that could lead to proving a premonoidal version of the classical Doplicher-Roberts theorem, and conjecture a possible solution to constructing a fibre-functor. Lastly we look at two variations on AQFT in which a causal order on double cones in Minkowski space is considered.