The RoboCup Soccer Simulator is a multi-agent soccer simulator used in competitions to simulate soccer playing robots. These competitionsare mainly held to promote robotics and AI research by providing a cheap and accessible way to program robot-like agents. In this report alearning multi-agent soccer team is implemented, described and tested.Policy Gradient Reinforcement Learning (PGRL) is used to train and alter the strategical decision making of the agents. The results show that PGRL improves the performance of the learningteam. But when the gap in performance between the learning team and the opponent is big the results were inconclusive. / RoboCup Soccer Simulator är en multiagent fotbollssimulator som används i tävlingar för att simulera robotar som spelar fotboll. Dessa tävlingar hålls huvudsakligen för att marknadsföra forskning inom robotik och articiell intelligens genom att tillhandahålla ett billigt och lättillgängligt sätt att programmera robotlika agenter. I denna rapportbeskrivs och testas en implementation av ett multiagentfotbollslag. PolicyGradiend Reinforcement Learning (PGRL) används för att träna ochförändra lagets beteende. Resultaten visar att PGRL förbättrar lagets prestanda, men närlagets prestanda skiljer sig avsevärt från motståndarens blir resultatetofullständigt.3

Robo Cup Soccer is a long-running yearly world wide robotics competition,in which teams of autonomous robot agents play soccer against each other.This report focuses on the 2D simulator variant, where no actual robots are needed and the agents instead communicate with a server which keeps trackof the game state. RoboCup Soccer 2D simulation has become a major topic of research for articial intelligence, cooperative behaviour in multi-agent systems, and the learning thereof. Some form of machine learning is mandatory if you want to compete at the highest level, as the problem is too complex for manualconguration of a teams decision making.This report nds that PGRL is a common method for machine learning in Robo Cup teams, it is utilized in some of the best teams in Robo Cup. The report also nds that PGRL is an effective form of machine learning interms of learning speed, but there are many factors which affects this. Most often a compromise have to made between speed of learning and precision. / Robo Cup Soccer är en årlig världsomspännande robotiktävling, i vilken lag av autonoma robotagenter spelar fotboll mot varandra. Denna rapport fokuserar på 2D-simulatorn, vilken är en variant där inga riktiga robotar behövs, utan där spelarklienterna istället kommunicerar med en server vilken håller reda på speltillståndet. RoboCup Soccer 2D simulation har blivit ett stort ämne för forskning inom articiell intelligens, samarbete och beteende i multi-agent-system, och lärandet därav. Någon form av maskininlärning är ett krav om man villkunna tävla på den högsta nivån, då problemet är för komplext för att beslutsfattandet ska kunna programmeras manuellt.Denna rapport finner att PGRL är en vanlig metod för maskininlärning i Robo Cup-lag, den används inom några av de bästa lagen i Robo Cup. Rapporten nner också att PGRL är en effektiv form av maskininlärningn är det gäller inlärningshastighet, men att det finns många faktorer som kan påverka detta. Oftast måste en avvägning ske mellan inlärningshastighet och precision.

Robotar blir allt mer komplexa och används i allt fler situationer. Detta ställer stora krav på styrningen av robotarna för att de ska kunna användas effektivt. Denna rapport avser att jämföra positionsbaserade och hastighetsbaserade styrmetoder mot varandra. Detta görs för att se om någon av dem är en effektivare styrmetod till att utföra en mängd uppgifter med en specifik simulerad robot som styrs med hjälp av antingen en Microsoft Xbox 360 Kinect elleren Microsoft Xbox 360 handkontroll. Resultaten från användartesterna visade att vardera styrmetod var överlägsen den andre för de uppgifter som var speciellt konstruerade för den styrmetoden. Däremot presterade de respektive styrmetoderna bättre än förväntat för de uppgifter som de inte var konstruerade för. Därför är de fortfarande lämpliga styrtekniker om implementationen görs mer ingående. / Robots are becoming more and more complex and are used in more and more situations. Thus creating tougher requirementsof the control of robots in order to as certain that the robots are effectively utilized. The aim of this report is to compare position and velocity based controltechniques against each other. This is done in order to seeif any of them are more effective than the other as a controltechnique for executing a set of tasks with a specific simulatedrobot that is controlled by either a Microsoft Xbox360Kinect or a Microsoft Xbox360 gamepad. The results from the user tests concluded that each technique was superior to the other on the tasks that were specifically designed for that control technique. The respective control techniquesdid however perform better than expected when used on the tasks that they were not designed for and therefore arestill viable options if the implementation is done more thorough

Sudoku and Jigsaw sudoku are two similar logic puzzles. The goal of the puzzles is to place numbers in a 9*9 grid until certain rules are met. In both Jigsaw sudoku and normal sudoku the numbers 1 to 9 needs to be placed in every row, column and box. The difference between the two puzzles is that in a normal sudoku every box is a symmetric 3*3 square, while in the jigsawv ariant the boxes have irregular, altough still nine cells big, boxes.When implementing algorithms for solving the normal sudoku, it normal touse the fact that all the boxes are symmetric. This will not work for the jigsaw sudoku though.In this report we will investigate the effectiveness of the three most common sudoku solving algorithms Rule Based backtracking, Human-Like solving and Dancing Links and how we arrived at the result that Human-Like solving was,in almost every case, the most effective algorithm for solving both sudoku and jigsaw sudoku. / Sudoku och Jigsaw sudoku är två likartade logik spel som går ut på att placera ut tal enligt vissa regler på en spelplan som har 9*9 rutor. I Både jigsaw sudoku och vanligt sudoku ska talen ett till nio finnas med i varje kolumn, rad och box exakt en gång. Det som skiljer dem åt är att i sudoku är boxarna symmetriska och 3*3 rutor stora medan i jigsaw sudoku har de varierande form av 9 rutor.Vid implementation av algoritmer för lösning av sudoku är det enkelt att använda symmetrin av hur de ser ut, medan det för jigsaw sudoku inte fungerar då boxarna ej är symmetriska.I denna rapport undersöker vi effektiviteterna hos de tre algoritmerna Rule Based backtracking, Human-Like solving och Dancing Link för att visa hur vi kom fram till resultatet att Human-Like solving i nästan alla fall var den effektivare algoritmen både för vanliga sudoku och jigsaw sudoku.

The purpose of this report is to evaluate squares in any Sudoku puzzle. The evaluation is based on how difficult the square’s number is to solve by using manual methods i.e. methods possible to use with pen and paper.To achieve this, manual methods have been implemented as algorithms into an application. A GUI presents the results in the form of a Sudoku solution and a matrix window to present which methods were needed for each single square.A number of Sudoku solving techniques were implemented and applied on both specific and randomly generated Sudokus. With this an evaluation of the squares could be demonstrated.Even if the program could not show the difficulty for all squares in some Sudokus, the conditions for further development of new techniques can be made with ease which can solve these more difficult Sudokus at a later stage. / Denna rapport har som mål att värdera rutor i ett Sudoku. Värderingen baseras på hur lätt eller svårt det är att få fram rutans nummer med mänskliga metoder.För att nå detta mål har mänskliga metoder för att lösa Sudokus implementerats som algoritmer i en application. Ett GUI presenterar resultat i form av sudoku lösning samt vilka metoder som krävdes för att lösa varje enskild ruta.Ett antal tekniker för att lösa sudokus implementerades och med både specifika och slumpmässigt genererade sudokus kunde det påvisas att en värdering kunde göras.Även om programmet inte lyckats få fram svårighetsgraden för alla sorters rutor i vissa sudokus så har förutsättningar skapats för att vidar utveckla tills alla rutor kan graderas.

Cross-language plagiarism is a type of plagiarism where texts from one languageare translated to another, concealing the origin of the text. This study tested if Google’s machine translation tool could be used as a preprocessor to a plagiarism detection tool in order to increase detection of cross-language plagiarism. It achieved positive results for detecting plagiarism in machine translated texts, while craftier plagiarised translations with higher degrees of obfuscation were harder to detect. Utilising even simple tools such as Google’s machine translation tool thus seems to indicate that steps to solving the problem of cross-language plagiarism can be taken.

Steganography is the technique that hides secret messages in seemingly inoccuous data. Steganalysis is the technique that is used to discover the use of steganography. Usuallyit is difficult to extract the exact hidden message because itis usually encrypted. Though often it is enough to merely uncover the use of steganography to reveal important information.In this report we discuss some common methods for steganography in images, as well as some methods of analysis,both general and targeted towards specific methods. We test how well the methods fare against each other and what one should consider when making use of steganography. According to our results, many steganographic methods need targeted analysis attacks to be discovered. Our advice is to avoid using the full potential capacity when embeddingdata. The hidden data should also be distributed randomly in the cover file.

School results are dropping in Sweden and actions are taken by the swedish government to prevent it. This report questions these actions.With a parallel between school and video games, in that they are both about teaching a student/player how to do something, a game is made to test how further explanation of the games mechanics affects the players ability to learn about them. The results are in line with other studies, overexplaining is hurting the players ability to learn about the game.

Natural Language Generation, NLG, is the translation ofraw data into legible and understandable text. It is currently being used in a variety of ways ranging from weatherforecasts to directions given by Google Maps. External NLG libraries are available for several programming languages, allowing more focus on the determining what would be included in the text generated.This report aims to investigate a suitable method of building an NLG system to be used with data provided by the Protracer software with the intent to provide golferswith text-based feedback of their game. Possible methods have been narrowed down to three approaches. The firstis simply outputting random feedback to the golfer with generic words and hope for the best. The second is usinga machine learning technique that takes shot parametersalong with a human interpretation of that shot. From this, the algorithm would acquire information about what buildsup a specific shot. Finally, the last method is using shotparameters along with human interpretation to construct an algorithm with observed threshold values to determine the shot type. Ultimately, the system constructed with the help of thereport was effective in classifying and describing golf ball trajectories. The difference between human interpretation and that of the system was negligible as the line between the classifications of a golf shot is very thin.

When it comes to Computer Go agents, the most common strategy is to traverse the game state tree to find as close to optimal solutions as possible. The goal is to sacrifice performance for a higher result accuracy. Going in the other direction — sacrificing accuracy for performance — is a less explored approach to the problem.In this report, a method combining the Copy-Move algorithm from the field of image forensics and computer vision with some pattern-based Computer Go digestion methods is tested against a large database of Go games. The partial soundness and fitness of the strategy is evaluated against a distinct subset of games by evaluating the predictability of human moves. The result is that while pattern-based Go strategies are still clearly inferior to game-tree search algorithms, they sometimes yield promising results that can be used to adjust the pruning approaches typically employed in tree traversal algorithms.1