Simulating Human Game Play for Level Difficulty Estimation with Convolutional Neural Networks
نویسندگان
چکیده
This thesis presents an approach to predict the difficulty of levels in a game by simulating game play following a policy learned from human game play. Using state-action pairs tracked from players of the game Candy Crush Saga, we train a Convolutional Neural Network to predict an action given a game state. The trained model then acts as a policy. Our goal is to predict the success rate (SR) of players, from the SR obtained by simulating game play. Previous state-ofthe-art was using Monte Carlo tree search (MCTS) or handcrafted heuristics for game play simulation. We benchmark our suggested approach against one using MCTS. The hypothesis is that, using our suggested approach, predicting the players’ SR from the SR obtained through the simulation, leads to better estimations of the players’ SR. Our results show that we could not only significantly improve the predictions of the players’ SR, but also decrease the time for game play simulation by at least 50 times. Referat Simulering av mänskligt spelande för bedömning av spelbanors svårighetsgrad med Convolutional Neural Networks. Den här avhandlingen presenterar ett tillvägagångssätt för att förutse svårighetsgrad av spelbanor genom spelsimulering enligt en strategi lärd från mänskligt spelande. Med användning av tillstånd-handlings par insamlade från spelare av spelet Candy Crush Saga, tränar vi ett Convolutional Neural Network att förutse en handling från ett givet tillstånd. Den tränade modellen agerar sedan som strategi. Vårt mål är att förutse success rate (SR) av spelare, från SR erhållen från spelsimulering. Tidigare state-of-the-art använde Monte Carlo tree search (MCTS) eller handgjorda heuristiker för spelsimulering. Vi jämför vårt tillvägagångssätt med MCTS. Hypotesen är att vårt föreslagna tillvägagångssätt leder till bättre förutsägelser av mänsklig SR från SR erhållen från spelsimulering. Våra resultat visar att vi inte bara signifikant kunde förbättra förutsägelserna av mänsklig SR utan också kunde minska tidsåtgången för spelsimulering med åtminstone en faktor 50.
منابع مشابه
Estimation of Hand Skeletal Postures by Using Deep Convolutional Neural Networks
Hand posture estimation attracts researchers because of its many applications. Hand posture recognition systems simulate the hand postures by using mathematical algorithms. Convolutional neural networks have provided the best results in the hand posture recognition so far. In this paper, we propose a new method to estimate the hand skeletal posture by using deep convolutional neural networks. T...
متن کاملInvestigating the performance of machine learning-based methods in classroom reverberation time estimation using neural networks (Research Article)
Classrooms, as one of the most important educational environments, play a major role in the learning and academic progress of students. reverberation time, as one of the most important acoustic parameters inside rooms, has a significant effect on sound quality. The inefficiency of classical formulas such as Sabin, caused this article to examine the use of machine learning methods as an alternat...
متن کاملProvide a Deep Convolutional Neural Network Optimized with Morphological Filters to Map Trees in Urban Environments Using Aerial Imagery
Today, we cannot ignore the role of trees in the quality of human life, so that the earth is inconceivable for humans without the presence of trees. In addition to their natural role, urban trees are also very important in terms of visual beauty. Aerial imagery using unmanned platforms with very high spatial resolution is available today. Convolutional neural networks based deep learning method...
متن کاملA New Method to Improve Automated Classification of Heart Sound Signals: Filter Bank Learning in Convolutional Neural Networks
Introduction: Recent studies have acknowledged the potential of convolutional neural networks (CNNs) in distinguishing healthy and morbid samples by using heart sound analyses. Unfortunately the performance of CNNs is highly dependent on the filtering procedure which is applied to signal in their convolutional layer. The present study aimed to address this problem by a...
متن کاملHand Gesture Recognition from RGB-D Data using 2D and 3D Convolutional Neural Networks: a comparative study
Despite considerable enhances in recognizing hand gestures from still images, there are still many challenges in the classification of hand gestures in videos. The latter comes with more challenges, including higher computational complexity and arduous task of representing temporal features. Hand movement dynamics, represented by temporal features, have to be extracted by analyzing the total fr...
متن کامل