Detecting emotional state of a child in a conversational computer game

The automatic recognition of user’s communicative style within a spoken dialog system framework, including the affective aspects, has received increased attention in the past few years. For dialog systems, it is important to know not only what was said but also how something was communicated, so that the system can engage the user in a richer and more natural interaction. This paper addresses the problem of automatically detecting “frustration”, “politeness”, and “neutral” attitudes from a child’s speech communication cues, elicited in spontaneous dialog interactions with computer characters. Several information sources such as acoustic, lexical, and contextual features, as well as, their combinations are used for this purpose. The study is based on a Wizard-of-Oz dialog corpus of 103 children, 7–14 years of age, playing a voice activated computer game. Three-way classification experiments, as well as, pairwise classification between polite vs. others and frustrated vs. others were performed. Experimental results show that lexical information has more discriminative power than acoustic and contextual cues for detection of politeness, whereas context and acoustic features perform best for frustration detection. Furthermore, the fusion of acoustic, lexical and contextual information provided significantly better classification results. Results also showed that classification performance varies with age and gender. Specifically, for the “politeness” detection task, higher classification accuracy was achieved for females and 10–11 years-olds, compared to males and other age groups, respectively.     

Life in the game of Go

The Oriental game of Go contains a unique method by which pieces, called stones, are captured and made safe from capture. A group of stones safe from capture is called safe, unconditionally alive, or similar terms. Life or its lack can be determined by lookahead through the game tree, at some expense. We present a graph-theoretic static analysis of the board arrangement which determines unconditional life or its lack, together with proofs of its equivalency to look ahead. An algorithm for the static evaluation is given and we argue that it is the preferable method for computer Go play. These results constitute the first realistic theorems in the theory of Go.     

Life in the game of Go

The Oriental game of Go contains a unique method by which pieces, called stones, are captured and made safe from capture. A group of stones safe from capture is called safe, unconditionally alive, or similar terms. Life or its lack can be determined by lookahead through the game tree, at some expense. We present a graph-theoretic static analysis of the board arrangement which determines unconditional life or its lack, together with proofs of its equivalency to look ahead. An algorithm for the static evaluation is given and we argue that it is the preferable method for computer Go play. These results constitute the first realistic theorems in the theory of Go.     

Temporal-difference search in computer Go

Temporal-difference learning is one of the most successful and broadly applied solutions to the reinforcement learning problem; it has been used to achieve master-level play in chess, checkers and backgammon. The key idea is to update a value function from episodes of real experience, by bootstrapping from future value estimates, and using value function approximation to generalise between related states. Monte-Carlo tree search is a recent algorithm for high-performance search, which has been used to achieve master-level play in Go. The key idea is to use the mean outcome of simulated episodes of experience to evaluate each state in a search tree. We introduce a new approach to high-performance search in Markov decision processes and two-player games. Our method, temporal-difference search, combines temporal-difference learning with simulation-based search. Like Monte-Carlo tree search, the value function is updated from simulated experience; but like temporal-difference learning, it uses value function approximation and bootstrapping to efficiently generalise between related states. We apply temporal-difference search to the game of 9×9 Go, using a million binary features matching simple patterns of stones. Without any explicit search tree, our approach outperformed an unenhanced Monte-Carlo tree search with the same number of simulations. When combined with a simple alpha-beta search, our program also outperformed all traditional (pre-Monte-Carlo) search and machine learning programs on the 9×9 Computer Go Server.     

Towards computer game studies

It is relatively stress-free to write about computer games as nothing too much has been said yet, and almost anything goes. The situation is pretty much the same when it comes to writing about games and gaming in general. The sad fact with alarming cumulative consequences is that they are under-theorized; there are Huizinga, Caillois and Ehrmann of course, and libraries full of board game studies,in addition to game theory and bits and pieces of philosophy – most notably those of Wittgenstein – but they won't get us very far with computer games. So if there already is or soon will be a legitimate field for computer game studies, this field is also very open to intrusions and colonisations from the already organized scholarly tribes. Resisting and beating them is the goal of our first survival game in this paper, as what these emerging studies need is independence, or at least relative independence.     

五子棋机器博弈系统评估函数的设计

针对五子棋机器博弈需借助棋型评估棋局产生的速度瓶颈,提出了棋型识别粒度与搜索深度相关联的多层架构评估函数设计方法。实验证实粗颗粒度估值在深层搜索时整体效率更高;多层次判读棋型能明显加快评估速度;走法生成函数引入快速评估,提前进行博弈树自然剪枝收效显著;非关键棋型依据棋局浮动分值平衡搜索深度,对五子棋亦见成效;以及估值函数针对性地延伸评估来减少地平线效应的开销更少;从而表明估值函数动态评估更加合理。     

Multipurpose strategic planning in the game of Go

A heuristic method for adversarial planning is developed to address the problem of multipurpose planning in the game of Go. Static analysis and dynamic look ahead on both strategic and tactical levels are used to generate possible goals and to identify interactions among the achievability of various goals. Strategic, multipurpose goals are composed of sets of interacting goals     

Teaching computer game design and construction

Computer gaming is a key component of the rapidly growing entertainment industry. While building computer games has typically been a commercial endeavor, we believe that designing and constructing a computer game is also a useful activity for educating students about geometric modeling and computer graphics. In particular, students are exposed to the practical issues surrounding topics such as geometric modeling, rendering, collision detection, character animation and graphical design. Moreover, building an advanced game provides students exposure to the real-world side of software engineering that they are typically shielded from in the standard computer class. In this paper, we describe our experiences with teaching a computer science class that focuses on designing and building the best game possible in the course of a semester. The paper breaks down a typical game into various components that are suited for individual student projects and discusses the use of modern graphical design tools such as Maya in building art for the game. We conclude with a rough timeline for developing a game during the course of a semester and review some of the lessons learned during the three years we have taught the class.     

机器博弈研究面临的各种挑战

让计算机学会下棋打牌,尤其和人类的精英对决,这是机器博弈领域长期的奋斗目标,也是人工智能学科极富挑战性的研究课题.为能在这一新兴的研究领域取得更快更多突破性进展,有力发挥机器博弈的"果蝇"作用,有必要很好地明确机器博弈研究当前面临哪些挑战性问题.从学术观念、实战博弈、理论发展、军事应用、国际接轨、普及提高及学生创新性培养等多角度阐述当前在机器博弈领域急需解决的主要问题,以期有更多的青年学者能够投身到这一极富挑战性的研究领域.     

Teaching computer science through game design

Playing computer games is a popular recreational activity for young people. Not surprisingly, many of these enthusiasts dream that one day they will develop computer games themselves. Developing computer games involves many aspects of computing, including computer graphics, artificial intelligence, human-computer interaction, security, distributed programming, simulation, and software engineering. Users who can't code a single line can use game maker to build games and learn object-oriented design.     

Maximizing the chance of winning in searching Go game trees

The current global selective search and decomposition search in Go typically back up territory scores. This approach is inherently flawed. We propose a new strategy of backing up “chance of winning”. We show how an evaluation function on the chance of winning can be constructed. Also we develop a probabilistic combinatorial game model and an algorithm for decomposition search to work with probabilistic outcomes in maximizing the chance of winning.     

Personality and enjoyment of computer game play

This paper introduces a research framework of game play based on a review of media enjoyment theories, personality theories, effects of computer game play, and technology acceptance model. The proposed framework suggests that an appropriate fit between characteristics of the player and gaming technology will result in greater enjoyment while social influence may moderate effects of the fit. An empirical study is carried out to investigate the relationship between enjoyment of computer game play and two personality traits (sensation seeking and self-forgetfulness). Hypotheses are proposed. A survey is conducted in two US universities. Results and implications are discussed.     

计算机扑克智能博弈研究综述

计算机博弈是人工智能领域的“果蝇”,备受人工智能领域研究者的关注,已然成为研究认知智能的有利平台。扑克类博弈对抗问题可建模成边界确定、规则固定的不完美信息动态博弈,计算机扑克 AI 需要具备不完全信息动态决策、对手误导欺诈行为识别以及多回合筹码和风险管理等能力。首先梳理了以德州扑克为代表的计算机扑克智能博弈的发展历程,其次针对计算机扑克智能博弈典型模型算法、关键技术以及存在的主要问题进行了综述分析,最后探讨了计算机扑克智能博弈的未来发展趋势和应用前景。     

一种面向指纹探测欺骗的智能博弈对抗机制

指纹探测作为网络侦察的重要组成部分,是攻击者成功实施网络攻击的先决条件。针对攻防双方在指纹探测过程中的博弈对抗特征,设计了一种新型对抗攻击者指纹探测的欺骗机制,并通过建立不完全信息动态博弈模型有效刻画指纹探测欺骗过程,在此基础上讨论了欺骗指纹生成的基本方法。针对扩展指纹库规模导致的解空间爆炸问题,提出了一种基于遗传算法思想的智能指纹混淆算法,即两阶段最优策略选取算法（two-stage optimal strategy selection algorithm,TSOSA）,并建立了仿真实验环境。结果表明,与传统的贪婪算法相比,TSOSA更加有效地隐藏了网络资产的真实指纹特征,降低了攻击者的成功探测概率,进而增强了网络的安全防护能力。     

Learning to predict life and death from Go game records

This article presents a new learning system for predicting life and death in the game of Go. It is called Gone. The system uses a multi-layer perceptron classifier which is trained on learning examples extracted from game records. Blocks of stones are represented by a large amount of features which enable a rather precise prediction of life and death. On average, Gone correctly predicts life and death for 88% of all the blocks that are relevant for scoring. Towards the end of a game the performance increases up to 99%. A straightforward extension for full-board evaluation is discussed. Experiments indicate that the predictor is an important component for building a strong full-board evaluation function.     

Ender's game redux [computer games]

In this article the author explains the context of his brother's e-mail, who is a US Army surgeon in Iraq. The e-mail concisely summarizes the convergence of entertainment technology and military training. He also describes the influence of game technology in his training.     

Urban hydrology in a computer game?

An increased interest in coupled natural and human systems motivates the simulation of dynamic interactions between humans and their environment. Simulation games often include this capability suggesting their use as research and/or educational tools, but this requires a somewhat realistic representation of environmental processes. This paper reviews the hydrology in the simulation game SimCity 4. The components of the hydrologic cycle included in the game relate mainly to drinking water supply, treatment and distribution. Groundwater, the sole source of drinking water, is present in unlimited quantity, but becomes polluted as a result of agricultural and industrial land uses. Water treatment plants are included, but in a somewhat unrealistic manner, in that they rapidly clean up aquifers in situ. The drinking water distribution infrastructure consists of water towers, pumps and pipes, but again, they are included in a somewhat unrealistic manner. Water towers and pumps both extract groundwater and are differentiated solely by their capacity, power usage and cost (rather than function). Besides for entertainment, the game should be valuable for educational purposes in lower level undergraduate courses to illustrate that/how water supply affects a city and vice versa. The general game architecture is capable of a more realistic representation and inclusion of additional components of the urban hydrologic cycle, which are discussed.     

A musical system for emotional expression

The automatic control of emotional expression in music is a challenge that is far from being solved. This paper describes research conducted with the aim of developing a system with such capabilities. The system works with standard MIDI files and develops in two stages: the first offline, the second online. In the first stage, MIDI files are partitioned in segments with uniform emotional content. These are subjected to a process of features extraction, then classified according to emotional values of valence and arousal and stored in a music base. In the second stage, segments are selected and transformed according to the desired emotion and then arranged in song-like structures.The system is using a knowledge base, grounded on empirical results of works of Music Psychology that was refined with data obtained with questionnaires; we also plan to use data obtained with other methods of emotional recognition in a near future. For the experimental setups, we prepared web-based questionnaires with musical segments of different emotional content. Each subject classified each segment after listening to it, with values for valence and arousal. The modularity, adaptability and flexibility of our system’s architecture make it applicable in various contexts like video-games, theater, films and healthcare contexts.