Playtesting plays a crucial role in video game production. The presence of gameplay issues and faulty design choices can be of great detriment to the overall player experience. Machine learning has the potential to be applied to automated playtesting solutions, removing mundane and repetitive testing, and allowing game designers and playtesters to focus their efforts on rewarding tasks. It is important in playtesting to consider the different playstyles players might use to adapt game design choices accordingly. With Reinforcement learning, it is possible to create high quality agents able to play and traverse complex game environments with fairly simple task-rewards. However, an automated playtesting solution must also be able to incorporate unique behaviour which mimic human playstyles. It can often be difficult to handcraft a quantitative style-reward to drive agent learning, especially for those with limited reinforcement learning experience, like game developers. MultiGAIL, Multimodal Generative Adversarial Imitation Learning, is a proposed learning algorithm able to generate autonomous agents imbued with human playstyles from recorded playstyle demonstrations. The proposed method requires no handcrafted style-reward, and can generate novel intermediate playstyles from demonstrated ones. MultiGAIL is evaluated in game environments resembling complex 3D games with both discrete and continuous action spaces. The playstyle the agent exhibits is easily controllable at inference with an auxiliary input parameter. Evaluation shows the agent is able to successfully replicate the underlying playstyles in human demonstrations, and that novel playstyles generate explainable action distributions indicative of the level of blending the auxiliary input declares. The results indicate that MultiGAIL could be a suitable solution to incorporate style behaviours in playtesting autonomous agents, and can be easily be used by those with limited domain knowledge of reinforcement learning. / ”Playtesting” har en viktig roll i TV-spelsutveckling. Fel i spel, såsom buggar och dålig speldesign kan drastiskt försämra spelupplevelsen. Maskininlärning kan användas för att automatisera testandet av spel och därmed ta bort behovet för människor att utföra repetitiva och tråkiga test. Spelutvecklare och speltestare kan då istället inrikta sig på mer nyttiga uppgifter. I playtesting så behöver de diverse spelstilar som spelare kan ha beaktas, så att spelutvecklare har möjligheten att anpassa spelet därefter. Förstärkande inlärning har använts för att skapa högkvalitativa agenter som kan spela och navigera komplexa spelmiljöer genom att definiera relativt simpla belöningsfunktioner. Dock är uppgiften att skapa en belöningsfunktion som formar agenten att följa specifika spelstilar en mycket svårare uppgift. Att anta att de utan förkunskaper inom maskininlärning och förstärkande inlärning, som spelutvecklare, ska kunna skapa sådana belöningsfunktioner är orealistiskt. MultiGAIL, Multimodal Generative Adversarial Imitation Learning", är en maskininlärningsalgoritm som kan generera autonoma agenter som efterföljer spelstilar med hjälp av tillgången till inspelade spelstilsdemonstrationer. Metoden kräver inga hårdkodade stilbelöningar och kan interpolera de spelstilarna funna i demonstrationerna, därav skapa nya beteenden för agenterna. MultiGAIL evalueras i spelmiljöer liknande komplexa 3D spel och kan använda både diskreta och kontinuerliga åtgärdsrum. Den spelstil agenten uppvisar kan enkelt kontrolleras vid inferens av en varierbar parameter. Vår evaluering visar att metoden kan lära agenten att korrekt imitera de spelstilar som definieras av inspelade demonstrationer. Nya spelstilar generade av MultiGAIL har förutsägbara beteenden utefter värdet på den varierande parametern. MultiGAIL kan mycket troligt användas för att skapa playtesting autonoma agenter som beter sig utefter specifika spelstilar utan att behöva definiera en belöningsfunktion.

Test Automation is becoming a more vital part of the software development cycle, as it aims to lower the cost of testing and allow for higher test frequency. However, automating manual tests can be difficult as they tend to require complex human interaction. In this thesis, we aim to solve this by using Imitation Learning as a tool for automating manual software tests. The software under test consists of a virtual simulation, connected to a physical input device in the form of a sight. The sight can rotate on two axes, yaw and pitch, which require human motion control. Based on this, we use a Behavioral Cloning approach with a k-NN regressor trained on human demonstrations. Evaluation of model resemblance to the human is done by comparing the state path taken by the model and human. The model task performance is measured with a score based on the time taken to stabilize the sight pointing at a given object in the virtual world. The results show that a simple k-NN regression model using high-level states and actions, and with limited data, can imitate the human motion well. The model tends to be slightly faster than the human on the task while keeping realistic motion. It also shows signs of human errors, such as overshooting the object at higher angular velocities. Based on the results, we conclude that using Imitation Learning for Test Automation can be practical for specific tasks, where capturing human factors are of importance. However, further exploration is needed to identify the full potential of Imitation Learning in Test Automation.

Québec Université Laval, Bibliothèque 2014

Tableau d'honneur de la Faculté des études supérieures et postdoctorales, 2019-2020 / Perse débute son oeuvre en rejetant systématiquement toutes les sources inspiratrices traditionnelles, dont la fontaine d’Hyppocrène, ce qui lui donne l’occasion de traiter Pégase de « canasson ». Alors que les interprétations d’ensemble réalisées par le passé sont faussées par une appréciation minimisant la construction systématique des Satires, l’objectif de cette étude est de démontrer que leur thème unificateur est la critique de la production / transmission et de la consommation de la littérature à l’époque néronienne. Dans le premier chapitre, en démontrant l’omniprésence des processus d’imitation et d’émulation dans le texte, puis en mettant au jour leur complexité et leur richesse sémantique, nous exposons la métatextualité des Satires, confirmant notre hypothèse de départ. L’analyse des Satires dans le cadre théorique du grotesque bakhtinien conduit dans un deuxième temps à révéler que le vice et la vertu y sont appariés respectivement à la mauvaise et à la bonne littérature et que Perse vise à détruire la première grâce à la philosophie. Par l’analyse de ce message subversif sous-jacent, nous expliquons quels sont les effets négatifs de la mauvaise littérature et les façons dont il faut s’y prendre pour la contrer. Dans le troisième chapitre enfin, grâce aux énoncés programmatiques et à diverses analyses stylistiques, nous donnons à connaître la cible de Perse : les poètes urbains philhellènes, cancres littéraires avides et présomptueux. Le style de Perse, en revanche, se distingue par son audace, son aspect mordax, sa modestie et sa romanité issue du mos maiorum. Grâce à notre étude, la cohérence des Satires, trop souvent tenues pour composites, apparaît nettement.

Achieving robust and reliable autonomous operation even in complex unstructured environments is a central goal of field robotics. As the environments and scenarios to which robots are applied have continued to grow in complexity, so has the challenge of properly defining preferences and tradeoffs between various actions and the terrains they result in traversing. These definitions and parameters encode the desired behavior of the robot; therefore their correctness is of the utmost importance. Current manual approaches to creating and adjusting these preference models and cost functions have proven to be incredibly tedious and time-consuming, while typically not producing optimal results except in the simplest of circumstances. This thesis presents the development and application of machine learning techniques that automate the construction and tuning of preference models within complex mobile robotic systems. Utilizing the framework of inverse optimal control, expert examples of robot behavior can be used to construct models that generalize demonstrated preferences and reproduce similar behavior. Novel learning from demonstration approaches are developed that offer the possibility of significantly reducing the amount of human interaction necessary to tune a system, while also improving its final performance. Techniques to account for the inevitability of noisy and imperfect demonstration are presented, along with additional methods for improving the efficiency of expert demonstration and feedback. The effectiveness of these approaches is confirmed through application to several real world domains, such as the interpretation of static and dynamic perceptual data in unstructured environments and the learning of human driving styles and maneuver preferences. Extensive testing and experimentation both in simulation and in the field with multiple mobile robotic systems provides empirical confirmation of superior autonomous performance, with less expert interaction and no hand tuning. These experiments validate the potential applicability of the developed algorithms to a large variety of future mobile robotic systems.

選擇性模仿是指嬰兒在不同情境中選擇性地模仿他人的行為，為當今發展心理學備受矚目的議題。在Gergely、Bekkering與Király（2002）著名的研究中，當實驗者的雙手自由放在桌上，示範以額頭碰盒子開燈，嬰兒偏好模仿此新奇動作；但當實驗者雙手緊抓毛毯示範相同的動作則未發現嬰兒有顯著的模仿偏好。有些研究者認嬰兒可以透過目的推理理解他人的意圖，並認為模仿是建立在對意圖的解讀之上；相反地，動作－效果整合理論則認為動作本身的執行困難度與動作－效果連結的穩定性才是影響嬰兒選擇性模仿的主因。 為了解決兩者長久以來對於嬰兒模仿的爭議，本研究修訂Gergely等人（2002）的光盒研究派典，將焦點放在過去一直未受到重視的因果效能概念，降低示範動作的因果效能，嬰兒在實驗過程中會發現示範動作不是每次都能成功讓光盒發亮，藉此釐清目的推理論與動作－效果整合理論對嬰兒選擇性模仿的解釋適當性。實驗1的結果重製了Gergely等人（2002）的實驗結果，實驗2A與實驗2B皆發現18個月大的嬰兒在因果效能較低的情境中很少會模仿示範動作，顯示嬰兒的模仿行為較符合動作－效果整合理論的觀點，主要是受到動作執行的困難度與動作－效果聯結的穩定性的影響。 / Selective imitation refers to a phenomenon which infants differentially imitate the demonstrated action in different contexts. Recently, it has also become a popular research topic in developmental psychology. Gergely, Bekkering and Király (2002) uncovered a classic example of selective imitation. They found that infants tend to imitate the action of touching a light box with their forehead when they saw a model perform the action with her hands placed on the table, but not when her hands were restricted by a blanket. Some researchers claim that infants can interpret others’ intention through teleological reasoning, and they consider infants’ imitation is based on decoding of intentionality. Conversely, ideomotor theory argues that imitation depends on difficulty of the action execution and the stability of link between action and its effect. To address the long-standing dispute with infants’ imitation, we revised the paradigm in Gergely et al. (2002) and focused on the concept of causal efficacy which had been long ignored in the past. Infant would find that the demonstrated action, sometimes won’t turn on the light during the experimentation. In experiment 1, we replicated the results obtained in Gergely et al. (2002). Experiment 2A and 2B both found that 18-month-old infants rarely imitated the demonstrated action when the causal efficacy was relatively low. These results are closer to the ideomotor approach viewpoint of imitation, and it reveals that infants’ imitation depends on difficulty of the action execution and the stability of link between action and effect.

Previous studies have established that when a subject’s attention is directed to a specific body part, the subject is able to move that body part faster than a body part their attention was not drawn to. This is known as the body compatibility effect, and it has been shown that this effect only occurs when viewing upright images of the human body. In this study, we presented control subjects and expert acrobats with inverted and upright stimuli. We hypothesized that the amount of time the acrobats spent inverted would result in the acrobats exhibiting body compatibility effects for both upright and inverted stimuli. Compatibility effects were observed in the upright condition for both groups, but neither group exhibited any compatibility effects in the inverted position. Unexpectedly the acrobats responded significantly faster to incongruent trials compared to the control subjects, leading to the conclusion that there must be some form of priming occurring concurrently with the body compatibility task allowing the acrobats to respond faster than the control participants.

Telecommunication has evolved tremendously from its origin to the present. Competition has grown in the telecommunications industry. One of the idiosyncratic characteristics of the mobile telecom services industry is the offering of homogenous products/services to the whole market, which indicates services being undifferentiated. The purpose of this paper is to study the differentiation strategies of mobile telecom operators and the impact of factors influencing the process of differentiation. The study will concentrate on the differentiation strategies of the mobile telecom service firms operating in Pakistan. The analysis model of this research was developed based on the determinants of product differentiation, relating to the tools that managers at mobile telecom service companies employ to execute differentiation strategies, and the factors influencing them. The empirical part of this study was conducted in January 2017. The multiple case study approach was adopted as a study method, and four case studies of the mobile telecom service companies operating in Pakistan were compared through cross-case analysis. Qualitative methods of data collection were employed and through semi-structured interviews primary data was gathered and secondary data was extracted from the websites and annual reports. The findings from the four case studies revealed that all the mobile operators opt for the differentiation strategies based on the determinants. It was examined from this research that these determinants are interrelated with each other. It was evident from the study of all the case companies that regulations affect the industry profits, increase the cost of upgrading the networks and infrastructures, causing a delay in the adoption of innovation, thereby influencing the differentiation strategy. The second factor influencing the differentiation process revealed in this study was competitive imitation, which caused convergence of strategies resulting in undifferentiated services even though operators tried to differentiate their services. The competitive imitation becomes easier due to the oligopoly structure of the mobile telecom industry.

This thesis concerns with media models of preschool child resilience. The theoretical part summarizes knowledge about developmental period of preschool child, social learning, imitation and human resilience. Further it is devoted to the media issue, especially media communication influence, child viewer and model learning per television transmission. The empirical part contains qualitative research of eighteen child animated cartoons. There were demanding situations and the coping strategies explored in the analysis. After their evaluation we recommended advisable child cartoons from the perspective of potential influence on resilience development of preschool child in the sense of self-efficacy, and comparison of Czech and foreign production. KEY WORDS Resilience, self- efficacy, imitation, media, television, animated cartoons, qualitative research

The aim of the diploma thesis was to observe the capability of imitation in orofacial area of three days old infants and analyze if the capability relates to quality of psychomotor development, thus whether it relates with a global motor model. This paper is a pilot study comprising seventeen infants. Each of them was supposed to attend four visits during the first six months of their life. It included visits in the first few days, between the fourth and the sixth week, the third month and the sixth month of their life. The psychomotor development was examined and within the first visit there was established communication with the child by means of eye contact and imitation. Each child's attempt at imitation and response was recorded. This thesis can serve as a basis for further research dealing with this topic that includes the imitation skill of mirror neurons related to psychomotor development.