Human Opponent Research Articles

Social contracts and human–computer interaction with simulated adapting agents

Game theory is commonly used to study social behavior in cooperative or competitive situations. One socioeconomic game, Stag Hunt, involves the trade-off between social and individual benefit by offering the option to hunt a low-payoff hare alone or a high-payoff stag cooperatively. Stag Hunt encourages the creation of social contracts as a result of the payoff matrix, which favors cooperation. By playing Stag Hunt with set-strategy computer agents, the social component is degraded because of the inability of subjects to dynamically affect the outcomes of iterated games, as would be the case when playing against another subject. However, playing with an adapting agent has the potential to evoke unique and complex reactions in subjects because of its ability to change its own strategy based on its experience over time, both within and between games. In the present study, 40 subjects played the iterated Stag Hunt with five agents differing in strategy: exclusive hare hunting, exclusive stag hunting, random, Win-Stay-Lose-Shift, and adapting. The results indicated that the adapting agent caused subjects to spend more time and effort in each game, exhibiting a more complicated path to their destination. This suggests that adapting agents exhibit behavior similar to human opponents, evoking more natural social responses in subjects.

Efficient bidding strategies for Cliff-Edge problems

In this paper, we propose an efficient agent for competing in Cliff-Edge (CE) and simultaneous Cliff-Edge (SCE) situations. In CE interactions, which include common interactions such as sealed-bid auctions, dynamic pricing and the ultimatum game (UG), the probability of success decreases monotonically as the reward for success increases. This trade-off exists also in SCE interactions, which include simultaneous auctions and various multi-player ultimatum games, where the agent has to decide about more than one offer or bid simultaneously. Our agent competes repeatedly in one-shot interactions, each time against different human opponents. The agent learns the general pattern of the population’s behavior, and its performance is evaluated based on all of the interactions in which it participates. We propose a generic approach which may help the agent compete against unknown opponents in different environments where CE and SCE interactions exist, where the agent has a relatively large number of alternatives and where its achievements in the first several dozen interactions are important. The underlying mechanism we propose for CE interactions is a new meta-algorithm, deviated virtual learning (DVL), which extends existing methods to efficiently cope with environments comprising a large number of alternative decisions at each decision point. Another competitive approach is the Bayesian approach, which learns the opponents’ statistical distribution, given prior knowledge about the type of distribution. For the SCE, we propose the simultaneous deviated virtual reinforcement learning algorithm (SDVRL), the segmentation meta-algorithm as a method for extending different basic algorithms, and a heuristic called fixed success probabilities (FSP). Experiments comparing the performance of the proposed algorithms with algorithms taken from the literature, as well as other intuitive meta-algorithms, reveal superiority of the proposed algorithms in average payoff and stability as well as in accuracy in converging to the optimal action, both in CE and SCE problems.

Emotional Responses to Victory and Defeat as a Function of Opponent

The experiment with 33 participants showed that the social relationship between players (playing a first-person shooter game against a friend or a stranger, and in single-player mode) influences phasic emotion-related psychophysiological responses to digital game events representing victory and defeat. Irrespective of opponent type, a defeat elicited increasing positive affect and decreasing negative affect (supporting earlier results), but it was most arousing when the opponent was a friend. Surprisingly, victory--in addition to positive emotion when playing against either human opponent--also elicited a negative response when the opponent was a friend. Responses to defeat in a single-player game were similar, but to a victory almost neutral. These results show that the social context affects not only the general experience, but also individual emotional responses, which has implications for adaptive game systems, experience research, and game design alike.

Evolving Tic-Tac-Toe Playing Algorithms Using Co-Evolution, Interactive Fitness and Genetic Programming

 Abstract—This paper presents a novel use of Genetic Programming, Co-Evolution and Interactive Fitness to evolve algorithms for the game of Tic-Tac-Toe. The selected tree-structured algorithms are evaluated based on a fitness-less double-game strategy and then compete against a human player. This paper will outline the evolution process which leads to producing the best Tic-Tac-Toe playing algorithm. The evolved algorithms have proven effective for playing against human opponents.

A Distinct Role of the Temporal-Parietal Junction in Predicting Socially Guided Decisions

To make adaptive decisions in a social context, humans must identify relevant agents in the environment, infer their underlying strategies and motivations, and predict their upcoming actions. We used functional magnetic resonance imaging, in conjunction with combinatorial multivariate pattern analysis, to predict human participants' subsequent decisions in an incentive-compatible poker game. We found that signals from the temporal-parietal junction provided unique information about the nature of the upcoming decision, and that information was specific to decisions against agents who were both social and relevant for future behavior.

An Immersive VR System for Sports Education

The development of new technologies has undoubtedly promoted the advances of modern education, among which Virtual Reality (VR) technologies have made the education more visually accessible for students. However, classroom education has been the focus of VR applications whereas not much research has been done in promoting sports education using VR technologies. In this paper, an immersive VR system is designed and implemented to create a more intuitive and visual way of teaching tennis. A scalable system architecture is proposed in addition to the hardware setup layout, which can be used for various immersive interactive applications such as architecture walkthroughs, military training simulations, sports game simulations, interactive theaters, and telepresence exhibitions. Realistic interaction experience is achieved through accurate and robust hybrid tracking technology, while the virtual human opponent is animated in real time using shader-based skin deformation. Potential future extensions are also discussed to improve the teaching/learning experience.

Material analysis for artificial muscle and touch sensing of cooperative biomimetic manipulators

There is a need for material analysis that can comfort the innovations of human intelligence towards providing solution to human disabilities. Humans throughout history have always sought to mimic the appearance, mobility, functionality, intelligent operation, and thinking process of biological creatures. This field of biologically inspired technology, having the moniker biomimetics, has evolved from making static copies of human and animals in the form of statues to the emergence of robots that operate with realistic appearance and behavior. Technology evolution led to such fields as artificial muscles, artificial intelligence, artificial vision, and biomimetic capabilities in materials science, mechanics, electronics, computing science, information technology, and many others. One of the newest fields is the artificial muscles. To promote faster advancement in the field, there was a challenge to the research and engineering community to develop a robotic arm that would wrestle against human opponent and win. In this paper, we have proposed a material that can be used in making artificial human parts like hands, fingers, limbs, which can provide greater solutions to various problems that are being faced in recent developments.

Children of the Fourth Revolution

It is a well-known fact that artificial intelligence (AI) research seeks both to reproduce the outcome of our intelligent behaviour by non-biological means, and to produce the non-biological equivalent of our intelligence. As a branch of engineering interested in intelligent behaviour reproduction, AI has been astoundingly successful. We increasingly rely on AI-related applications (smart technologies) to perform tasks that would be simply impossible by un-aided or un-augmented human intelligence. But as a branch of cognitive science interested in intelligence production, AI has been a dismal disappointment. Productive AI does not merely underperform with respect to human intelligence; it has not joined the competition yet. The fact that Watson—IBM’s system capable of answering questions asked in natural language—recently won against its human opponents when playing Jeopardy! only shows that artefacts can be smart without being intelligent. The two souls of AI, the engineering and the cognitive one, have often engaged in fratricidal feuds for intellectual predominance, academic power, and financial resources. That is partly because they both claim common ancestors and a single intellectual inheritance: a founding event, the Dartmouth Summer Research Conference on Artificial Intelligence in 1956, and a founding father, Turing, with his machine and its computational limits, and then his famous test. It hardly helps that a simulation might be used in order to check both whether the simulated source has been produced, and whether the targeted source’s behaviour or performance has been reproduced or even surpassed. The misalignment of their goals and results has caused endless and mostly pointless diatribes. Defenders of AI point to the strong results of reproductive, engineering AI, whereas detractors of AI point to the weak results of productive, cognitive AI. Many of the current speculations on the so-called singularity issue have their roots in such confusion. Philos. Technol. (2011) 24:227–232 DOI 10.1007/s13347-011-0042-7

Effect of Opponent Type on Moral Emotions and Responses to Video Game Play

This study suggests that fighting against different types of opponents in video games (e.g., human opponents vs. monster opponents) may lead to different emotional responses and moral judgments toward game characters. Based on Bandura's moral disengagement theory, this study proposes that shooting at monster opponents makes game players feel less guilty and judge the player-controlled character as more morally justified. An experiment was conducted in which participants played shooting games with either human opponents or monster opponents. The results show that when playing against monster opponents, participants felt both less ashamed and less guilty, reported enjoying the game more, and judged their character as more justified than participants who played against human opponents.

Measurements of long-range suppression in human opponent S-cone and achromatic luminance channels

Cortical responses to spatially discrete patches of achromatic luminance contrast can be altered by the presence of high-contrast, spatially remote "surrounds" and this achromatic "surround suppression" has been the subject of much recent research. However, the nature of long-range contrast normalization in chromatic signals has been less studied. Here we use a combination of neuroimaging data from source-imaged EEG and two different psychophysical measures of surround suppression to study contrast normalization in stimuli containing achromatic luminance and S-cone-isolating contrast. In an appearance matching task, we find strong within-channel but little between-channel suppression. However, using a contrast increment detection task, we do find evidence for weak but significant between-channel effects. Our neural measurements agree with the appearance matching data, showing significant within-channel suppression and no significant interactions between signals initiated in different pre-cortical pathways. We hypothesize that appearance judgments and V1 population responses are dominated by neurons with chromatically matched classical and extra-classical surrounds while contrast increment detection tasks rely on a subpopulation of neurons that have extra-classical surrounds sensitive to both chromatic and achromatic contrasts. Our psychophysical and source-imaged EEG results are consistent with a hypothesis based on natural scene statistics that long-range contrast normalization in early visual system is largely driven by signals within the same chromatic channel.

The effect of human opponent on autonomic activity during versus fighting game

The effect of human opponent on autonomic activity during versus fighting game

主成分分析を用いたヒトのスキルの再現とロボットへの移植

This paper discusses human skills enabling rapid adaptations to a changing environment as seen when a table tennis player hits an incoming ball and presents how to transfer them to a robot. We consider that human skills can be classified into motor skills and cognitive skills. As for motor skills, a function involving precise movement of limbs with the intent to perform a specific act (hitting a ball), we extract motor primitives from human performance data. As for cognitive skills, a function involving a meaningful response to external stimuli, we find correlation of the stimulus (the ball's state) with the timing of response (starting to swing a racket). We also present table tennis rallies with a human opponent performed by a robot to which these skills are transferred.

Metabolic changes associated with playing active video game against a human and computer opponent

With 58 million individuals being overweight and another 40 million obese in the United States of America, active video gaming may become a means to improve physical fitness and possibly even more so when playing against a human opponent as compared to a computer opponent. The purpose of this study was to determine the changes in heart rate, oxygen consumption and energy expenditure while playing Nintendo Wii Boxing™ against a human and computer opponent. Twenty adults (10 males and 10 females) between 19 and 25 years of age played Nintendo Wii Boxing™ for 15 minutes. The subjects were randomised to play against a human or computer opponent while heart rate, oxygen consumption and energy expenditure were measured. Heart rate, oxygen consumption and energy expenditures were all significantly (p ≤ 0.05) higher duringthe VO2max assessment. Heart rates were significantly higher when playing against a human opponent (103.8 ± 4.31 bpm) and the computer opponent (104.6 ± 4.58 bpm) when compared to when at rest (75.4 ± 2.90 bpm). No significant differences were found in heart rates whencomparing the two video game opponents or the males and females. Oxygen consumption was significantly higher when playing against both the human (14.6 ± 1.80 ml•min-1) and computer (14.4 ± 1.66 ml•min-1) opponents than at rest (4.4 ± 0.51 ml•min-1), with no differences between gender or video game opponent. Energy expenditure was significantly higher when playing against a human (3.3 ± 0.4 kcal•min-1) and computer (3.2 ± 0.3 kcal•min-1) opponent when compared to when at rest (1.1 ± 0.1 kcal•min-1), while no significant differences were found between the two video game opponents or males and females. While the findings indicate that playing against a human or computer opponent does not alter the magnitude of increase in the metabolic responses, the increases in metabolic responses observed were significantly higherthan when at rest classifying active video gaming as a light intensity activity similar to brisk walking, skipping and stair walking. However, this increase in metabolic responses may not enhance physical well-being, and as such does not provide an adequate stimulus to optimally enhance fitness.

Energy Cost Of Physically Active Video Gaming Against A Human Or Computer Opponent

Playing a physically active video game increases energy expenditure above that of sedentary video game play. And anecdotal reports suggest that people play harder against other people then against the computer system. However, the energy expenditure of playing a physically active video game against another person has not been evaluated. Furthermore, most of the research on energy expenditure during physically active video game play has been conducted in children even though young adults represent a large portion of the video game market. PURPOSE: To determine if there is a difference in energy expenditure while playing Nintendo Wii Boxing against a Human or Computer opponent, and to evaluate the energy expenditure in young adults. METHODS: Twenty college-aged adults (10 males, 22.5 ± 0.5 y:10 females, 21.0 ± 0.4 y) were measured for body composition and maximal aerobic capacity (VO2max) before playing Nintendo Wii Boxing for 15 minutes against a human or computer opponent, in a randomized manner, while heart rate, oxygen consumption, and energy expenditure were measured. RESULTS: Heart rate, oxygen consumption, and energy expenditure were all higher (P<0.05) at VO2max than any other condition. Heart rates (beats/min) while playing the video game were higher (P<0.05) for both the Human (103.8 ± 4.3) and Computer (104.6 ± 4.6) opponent than at rest (75.4 ± 2.9), with no differences between gender or video game opponent. Oxygen consumption (ml/kg/min) while playing the video game was higher (P<0.05) for both the Human (14.6 ± 1.80) and Computer (14.4 ± 1.66) opponent than at rest (4.4 ± 0.51), with no differences between gender or video game opponent. CONCLUSIONS: The present data support previous investigations indicating that playing a physically active video game increases heart rate, oxygen consumption, and energy expenditure, but the magnitude of increase is not sufficient to classify physically active video game play as even moderate intensity exercise. These data also indicate that the magnitude of increase in energy expenditure while playing a physically active video game is similar in children and young adults. The present data further suggest that playing against a computer or human opponent does not alter the magnitude of increase in energy expenditure associated with physically active video game play.

Agents of History

World War II research into cryptography and computing produced methods, instruments and research communities that informed early research into artificial intelligence (AI) and semi-autonomous computing. Alan Turing and Claude Shannon in particular adapted this research into early theories and demonstrations of AI based on computers’ abilities to track, predict and compete with opponents. This formed a loosely bound collection of techniques, paradigms, and practices I call crypto-intelligence. Subsequent researchers such as Joseph Weizenbaum adapted crypto-intelligence but also reproduced aspects of its antagonistic precepts. This was particularly true in the design and testing of chat bots. Here the ability to trick, fool, and deceive human and machine opponents was a premium, and practices of agent abuse were admired and rewarded. Recognizing the historical genesis of this particular variety of abuse can help researchers develop less antagonistic methodologies.

Enhancing Artificial Intelligence on a Real Mobile Game

Mobile games represent a killer application that is attracting millions of subscribers worldwide. One of the aspects crucial to the commercial success of a game is ensuring an appropriately challenging artificial intelligence (AI) algorithm against which to play. However, creating this component is particularly complex as classic search AI algorithms cannot be employed by limited devices such as mobile phones or, even on more powerful computers, when considering imperfect information games (i.e., games in which participants do not a complete knowledge of the game state at any moment). In this paper, we propose to solve this issue by resorting to a machine learning algorithm which uses profiling functionalities in order to infer the missing information, thus making the AI able to efficiently adapt its strategies to the human opponent. We studied a simple and computationally light machine learning method that can be employed with success, enabling AI improvements for imperfect information games even on mobile phones. We created a mobile phone-based version of a game calledGhostsand present results which clearly show the ability of our algorithm to quickly improve its own predictive performance as far as the number of games against the same human opponent increases.

Aggression in the Laboratory: Problems with the Validity of the Modified Taylor Competitive Reaction Time Test as a Measure of Aggression in Media Violence Studies

ABSTRACT Many laboratory studies of aggression use a measure known as the modified Taylor Competitive Reaction Time Test (TCRTT), for which validation studies are lacking. Using sound blasts administered by the participant against a fictional human opponent, the TCRTT also allows for multiple methods of measuring aggression. The validity of the TCRTT was tested in 53 college student participants. Participants took a self-report measure of aggressiveness as well as neuropsychological measures of frontal lobe functioning predictive of aggression. Results were not supportive of the TCRTT's validity and indicated concerns regarding the use of the TCRTT as a measure of aggression. Results suggest that labaratory studies of media violence using the TCRTT are of questionable validity.

Toward a Competitive Pool-Playing Robot

Deep Green is a vision-based, intelligent robotic system that currently shoots pool at a better-than-amateur level, with the ultimate goal of challenging a proficient human opponent at a championship level. The system's robotic aspects rely primarily on computer vision. The system is centered on a 3-degree-of-freedom gantry robot mounted to the ceiling to avoid impeding human access to the table.

A Hybrid Fuzzy ANN System for Agent Adaptation in a First Person Shooter

The aim of developing an agent, that is able to adapt its actions in response to their effectiveness within the game, provides the basis for the research presented in this paper. It investigates how adaptation can be applied through the use of a hybrid of AI technologies. The system developed uses the predefined behaviours of a finite-state machine and fuzzy logic system combined with the learning capabilities of a neural computing. The system adapts specific behaviours that are central to the performance of the bot (a computer-controlled player that simulates a human opponent) in the game, with the paper’s main focus being on that of the weapon selection behaviour; selecting the best weapon for the current situation. As a development platform, the project makes use of the Quake 3 Arena engine, modifying the original bot AI to integrate the adaptive technologies.

On the Robustness of the Winner’s Curse Phenomenon

We set out to find ways to help decision makers overcome the “winner’s curse,” a phenomenon commonly observed in asymmetric information bargaining situations, and instead found strong support for its robustness. In a series of manipulations of the “Acquiring a Company Task,” we tried to enhance decision makers’ cognitive understanding of the task. We did so by presenting them with different parameters of the task, having them compare and contrast these different parameters, giving them full feedback on their history of choices and resulting outcomes, and allowing them to interact with a human opponent instead of a computer program. Much to our surprise, none of these manipulations led to a better understanding of the task. Our results demonstrate and emphasize the robustness of the winner’s curse phenomenon.