Search

Multi-player action recognition for automatic analysis in sports is the subject of increasing attention. Trajectory-tracking technology is key for accurate recognition, but little research has focused on this aspect, especially for non-professional matches. Here, we study multi-player tracking in the most popular and complex sport among non-professionals—soccer. In this non-professional soccer player tracking (NPSPT) challenge, single-view-based motion recording systems for continuous data collection were installed in several soccer fields, and a new benchmark dataset was collected. The dataset consists of 17 2-min long super-high-resolution videos with diverse game types consistently labeled across time, covering almost all possible situations for multi-player detection and tracking in real games. A comprehensive evaluation was conducted on the state-of-the-art multi-object-Tracking (MOT) systems, revealing insights into player tracking in real games. Our challenge introduces a new dimension for researchers in the player recognition field and will be beneficial to further studies. [ABSTRACT FROM AUTHOR]

Poker has been considered a challenging problem in both artificial intelligence and game theory because poker is characterized by imperfect information and uncertainty, which are similar to many realistic problems like auctioning, pricing, cyber security, and operations. However, it is not clear that playing an equilibrium policy in multi-player games would be wise so far, and it is infeasible to theoretically validate whether a policy is optimal. Therefore, designing an effective optimal policy learning method has more realistic significance. This paper proposes an optimal policy learning method for multi-player poker games based on Actor-Critic reinforcement learning. Firstly, this paper builds the Actor network to make decisions with imperfect information and the Critic network to evaluate policies with perfect information. Secondly, this paper proposes a novel multi-player poker policy update method: asynchronous policy update algorithm (APU) and dual-network asynchronous policy update algorithm (Dual-APU) for multi-player multi-policy scenarios and multi-player sharing-policy scenarios, respectively. Finally, this paper takes the most popular six-player Texas hold 'em poker to validate the performance of the proposed optimal policy learning method. The experiments demonstrate the policies learned by the proposed methods perform well and gain steadily compared with the existing approaches. In sum, the policy learning methods of imperfect information games based on Actor-Critic reinforcement learning perform well on poker and can be transferred to other imperfect information games. Such training with perfect information and testing with imperfect information models show an effective and explainable approach to learning an approximately optimal policy. [ABSTRACT FROM AUTHOR]

In this article, a novel online method for multi-player non-zero-sum (NZS) differential games of nonlinear partially unknown continuous time (CT) systems with control constraints is developed based on neural networks (NN). The issue of multi-player NZS games with saturated actuator is elaborately analyzed and the unknown dynamics model is learned by applying identifier NN. Different from using the standard identifier-actor-critic framework of adaptive dynamic programming (ADP), the proposed method uses only identifier networks and critic networks for all the players to solve the coupled Hamilton-Jacobi (HJ) equations for multi-player NZS games, which could effectively simplify the algorithm and save computing resources. Moreover, a tuning law which utilizes the gradient descent method is designed for each critic network. Meanwhile, to remove the requirement for the initial stabilizing control, a novel stability term is designed to ensure the system stability during the training phase of the critic NN. By the means of Lyapunov approach, it is proven that the system states, the critic network weight estimation errors and the obtained control are all uniformly ultimately bounded (UUB). Finally, two numerical examples are simulated to illustrate the validity of the developed method for multi-player NZS games with control constraints.

Multi-player action recognition for automatic analysis in sports is the subject of increasing attention. Trajectory-tracking technology is key for accurate recognition, but little research has focused on this aspect, especially for non-professional matches. Here, we study multi-player tracking in the most popular and complex sport among non-professionals—soccer. In this non-professional soccer player tracking (NPSPT) challenge, single-view-based motion recording systems for continuous data collection were installed in several soccer fields, and a new benchmark dataset was collected. The dataset consists of 17 2-min long super-high-resolution videos with diverse game types consistently labeled across time, covering almost all possible situations for multi-player detection and tracking in real games. A comprehensive evaluation was conducted on the state-of-the-art multi-object-Tracking (MOT) systems, revealing insights into player tracking in real games. Our challenge introduces a new dimension for researchers in the player recognition field and will be beneficial to further studies.

Poker has been considered a challenging problem in both artificial intelligence and game theory because poker is characterized by imperfect information and uncertainty, which are similar to many realistic problems like auctioning, pricing, cyber security, and operations. However, it is not clear that playing an equilibrium policy in multi-player games would be wise so far, and it is infeasible to theoretically validate whether a policy is optimal. Therefore, designing an effective optimal policy learning method has more realistic significance. This paper proposes an optimal policy learning method for multi-player poker games based on Actor-Critic reinforcement learning. Firstly, this paper builds the Actor network to make decisions with imperfect information and the Critic network to evaluate policies with perfect information. Secondly, this paper proposes a novel multi-player poker policy update method: asynchronous policy update algorithm (APU) and dual-network asynchronous policy update algorithm (Dual-APU) for multi-player multi-policy scenarios and multi-player sharing-policy scenarios, respectively. Finally, this paper takes the most popular six-player Texas hold ’em poker to validate the performance of the proposed optimal policy learning method. The experiments demonstrate the policies learned by the proposed methods perform well and gain steadily compared with the existing approaches. In sum, the policy learning methods of imperfect information games based on Actor-Critic reinforcement learning perform well on poker and can be transferred to other imperfect information games. Such training with perfect information and testing with imperfect information models show an effective and explainable approach to learning an approximately optimal policy.

Texting while driving has been shown to impair driving performance with the greatest probability of leading to an accident. This is a great concern with young and inexperienced drivers, who are reported to be the most prolific users of texting while driving and are disproportionately involved in car crashes as compared to their experienced and older counterparts. HazardWarning Systems (HWSs) have been researched to reduce distracted driving and improve driving performance. The first purpose of this study is to showcase a game-based, multi-player, online simulated training (GMOST) application with an integrated HWS. The second is to examine whether such an HWS integrated into the GMOST improves young and inexperienced drivers' hazard perception skills, as measured by hazard reaction time (HRT) and horizontal road scanning (HS). A total of 22 high school students from a private school participated in this study. To determine the effects of HWS, a 2 × 2 ANOVA and a 2 × 2 MANOVA were run. The results of this study suggest that the GMOST with integrated HWS leads to earlier detection and reaction to hazards as well as wider HS by novice drivers. Therefore, this study reports that HWSs improve novice distracted drivers' hazard perception skills. Accordingly, a wide-spread use of the GMOST-like training applications by novice drivers would be a proactive approach to lower accident rates caused by texting while driving. [ABSTRACT FROM AUTHOR]

Texting while driving has been shown to impair driving performance with the greatest probability of leading to an accident. This is a great concern with young and inexperienced drivers, who are reported to be the most prolific users of texting while driving and are disproportionately involved in car crashes as compared to their experienced and older counterparts. Hazard Warning Systems (HWSs) have been researched to reduce distracted driving and improve driving performance. The first purpose of this study is to showcase a game-based, multi-player, online simulated training (GMOST) application with an integrated HWS. The second is to examine whether such an HWS integrated into the GMOST improves young and inexperienced drivers’ hazard perception skills, as measured by hazard reaction time (HRT) and horizontal road scanning (HS). A total of 22 high school students from a private school participated in this study. To determine the effects of HWS, a 2 × 2 ANOVA and a 2 × 2 MANOVA were run. The results of this study suggest that the GMOST with integrated HWS leads to earlier detection and reaction to hazards as well as wider HS by novice drivers. Therefore, this study reports that HWSs improve novice distracted drivers’ hazard perception skills. Accordingly, a wide-spread use of the GMOST-like training applications by novice drivers would be a proactive approach to lower accident rates caused by texting while driving.

Background: Exergames have the potential to significantly increase physical activity in children. Studies to date have shown mixed results and often rely on self-reported data. Multi-player gaming may augment participation.Purpose: The purpose of the study was to examine children's adherence behaviors in multi-player online exergames compared to a single-player condition within a home environment.Methods: Seventy-two children, aged 9-12 years, who were not meeting physical activity guidelines at baseline, were allocated to the multi-player or single-player condition. Six-week cycle-based exergaming trials took place 5 day/week in the early evening with online game supervision. Bike use was objectively recorded via game logs.Results: Adherence was high throughout the trial. Play session duration was M = 37.65 (SD = 15.39) min/day, and overall play duration was M = 133.45 (SD = 81.27) min in Week 1 and M = 77.23 (SD = 84.09) min in Week 6. Total physical activity was significantly higher at 6 weeks compared to baseline (p = .01, ηp2 = .13). There was no significant difference in play duration between conditions (p = .57, ηp2 = .01).Conclusion: This trial objectively demonstrated that exergames can promote high adherence levels. Multi-player capabilities did not augment adherence levels. Introducing new games throughout the trial may have motivated participants to keep playing, regardless of whether play was against real or artificial opponents. Weekly play duration decreased due to a significant drop in play frequency. For children who enjoy exergames, innovative solutions to promote more frequent exergame play are needed.Clinical This Registration: NCT02032667. [ABSTRACT FROM AUTHOR]

We introduce a class of impartial combinatorial games, Multi-player Last Nim with Passes, denoted by MLNim(s)(N,n): there are N piles of counters which are linearly ordered. In turn, each of n players either removes any positive integer of counters from the last pile, or makes a choice ‘pass’. Once a ‘pass’ option is used, the total number s of passes decreases by 1. When all s passes are used, no player may ever ‘pass’ again. A pass option can be used at any time, up to the penultimate move, but cannot be used at the end of the game. The player who cannot make a move wins the game. The aim is to determine the game values of the positions of MLNim(s)(N,n) for all integers N≥1 and n≥3 and s≥1. For n>N+1 or n=N+1≥3, the game values are completely determined for any s≥1. For 3≤n≤N, the game values are determined for infinitely many triplets (N, n, s). We also present a possible explanation why determining the game values becomes more complicated if n≤N. [ABSTRACT FROM AUTHOR]

Destiny is a hybrid online shooter sharing features with Massively Multi-Player Online Games and first-person shooters and is the to date the most expensive digital game produced. It has attracted millions of players to compete or collaborate within a persistent online environment. In multiplayer online games, the interaction between the players and the social community that forms in persistent games forms a crucial element in retaining and entertaining players. Social networks in games have thus been a focus of research, but the relationships between player behavior, performance, engagement and the networks forming as a result of interactions, are not well understood. In this paper, a large-scale study of social networks in hybrid online games/shooters is presented. In a network of over 3 million players, the connections formed via direct competitive play are explored and analyzed to answer five main research question focusing on the patterns of players who play with the same people and those who play with random groups, and how differences in this behavior influence performance and engagement metrics. Results show that players with stronger social relationships have a higher performance based on win/loss ratio and kill/death ratio, as well as a tendency to play more and longer. [ABSTRACT FROM AUTHOR]

A novel method is presented to solve the nonzero-sum multi-player Nash differential game. It combines the use of the variation and Legendre pseudo-spectral methods. By the variation method, the original game is converted into a regular optimal control problem, avoiding the need to solve the associated Hamilton-Jacobi equation. Then the latter problem is converted into a common nonlinear programming problem via the Legendre pseudo-spectral method, by which the saddle-point for the original game can be achieved accurately. As an illustration, the air combat between two pursuers and an evader is formulated as a nonzero-sum differential game. The simulation results show that numerical solutions can converge to the saddle-points from different initial conditions, which demonstrates the feasibility and validity of the proposed method. Because the solution process requires little computational time, this method will allow for the development of a real time air combat control strategy. In addition, the simulations show that if the initial states of the two pursuers are fixed, there is an optimal initial heading angle for the evader to delay the interception time most effectively. Copyright © 2016 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

In this paper, a synchronous solution method for multi-player zero-sum games without system dynamics is established based on neural network. The policy iteration (PI) algorithm is presented to solve the Hamilton–Jacobi–Bellman (HJB) equation. It is proven that the obtained iterative cost function is convergent to the optimal game value. For avoiding system dynamics, off-policy learning method is given to obtain the iterative cost function, controls and disturbances based on PI. Critic neural network (CNN), action neural networks (ANNs) and disturbance neural networks (DNNs) are used to approximate the cost function, controls and disturbances. The weights of neural networks compose the synchronous weight matrix, and the uniformly ultimately bounded (UUB) of the synchronous weight matrix is proven. Two examples are given to show that the effectiveness of the proposed synchronous solution method for multi-player ZS games. [ABSTRACT FROM AUTHOR]

This article examines the different types of knowledge that MMORPG players develop as they learn and play a game. Data is drawn from a year of case-study/ethnography based research sessions with a ten-member raiding group in the game World of Warcraft . Drawing from the work of Aristotle, contemporary game studies scholarship, actor network theory, and the concept of “practices,” what is presented here is a matrix of complex gamer knowledge types intended not only to expand the reader’s understanding of the robust variations and nuances in gamer knowledge but also to serve as a potential example of how to articulate that richness in future research. The matrix is accompanied by rationale and examples of how the knowledges function in game experiences. [ABSTRACT FROM AUTHOR]

Krawec (2012) introduced a method of analyzing multi-player impartial games, and derived a recursive function capable of determining which of the n players has a winning strategy. The present paper is devoted to the game “Misère N -pile Nim with n players”, abbreviated by MiNim( N , n ), assuming that the standard alliance matrix is adopted. The game values of MiNim( N , n ) are completely determined for three cases: n > N + 1 , n = N + 1 and n = N . The case n < N is more complicated, we present the game values of MiNim( N , n ) only for n = 3 and N = 4 . [ABSTRACT FROM AUTHOR]

Zero-determinant (ZD) strategies that allow a player to unilaterally control the linear combinations of its own and other players’ expected rewards in iterated games have recently found wide applications. However, existing ZD strategies mainly focus on some specific scenarios with restrictions on the number of players or actions a player can take. Targeting wider applications and better performance, the ZD strategies along with corresponding existence conditions for general multi-player multi-action iterated games are developed in this work, including existing ones as special cases. In addition, an interesting fact that every player can have at most one master player (that can control the expected reward of the given player) is revealed. [ABSTRACT FROM PUBLISHER]

Abstract: Brain–computer interfaces (BCIs) have started to be considered as game controllers. The low level of control they provide prevents them from providing perfect control but allows the design of challenging games which can be enjoyed by players. Evaluation of enjoyment, or user experience (UX), is rather a new practice with BCI applications. The UX of multi-player BCI games, or co-experience, is especially scarcely assessed. In the study we report in this paper, we relied on observation analysis of social interaction to infer co-experience of pairs of players while they were playing a collaborative multi-player game using BCI. To investigate the effect of perceived level of control on co-experience, we compared BCI control to a more reliable mouse control. In order to investigate the co-experience related factors beyond the level of control, we compared BCI control to an equally reliable control mechanism. Our results show that low level of control dampened collaborative interaction while enhancing emotional interaction within pairs of players. Thus, the challenge of playing a computer game using BCI can influence the co-experience. [Copyright &y& Elsevier]

While shows like The X-Files and 24 have merged conspiracy theories with popular science (fictions), some video games have been pushing the narrative even further. Electronic Art's Majestic game was released in July 2001 and quickly generated media buzz with its unusual multi-modal gameplay. Mixing phone calls, faxes, instant messaging, real and "fake' websites, and email, the game provides a fascinating case of an attempt at new directions for gaming communities. Through story, mode of playing, and use of technology, Majestic highlights the uncertain status of knowledge, community and self in a digital age; at the same time, it allows examination of alternative ways of understanding games' role and purpose in the larger culture. Drawing on intricate storylines involving government conspiracies, techno-bio warfare, murder and global terror, players were asked to solve mysteries in the hopes of preventing a devastating future of domination. Because the game drew in both actual and Majestic -owned/-designed websites, it constantly pushed those playing the game right to borders where simulation collides with " factuality'. Given the wide variety of "legitimate' conspiracy theory, alien encounters and alternative science web pages, users often could not distinguish when they were leaving the game's pages and venturing into " real' World Wide Web sites. Its further use of AOL's instant messenger system, in which gamers spoke not only to bots but to other players, pushed users to evaluate constantly both the status of those they were talking to and the information being provided. Additionally, the game required players to occupy unfamiliar subject positions, ones where agency was attenuated, and which subsequently generated a multi-layered sense of unease among players. This mix of authentic and staged information in conjunction with technologically mediated roles highlights what are often seen as phenomenon endemic to the Internet itself; that is, the destabilization of categories of knowing, relating, and being. [ABSTRACT FROM AUTHOR]

In order to analyze a multi-player linear-quadratic alternating-move dynamicgame, this paper develops a solution method by making use of the similarstructure of this game and a simultaneous-move dynamic game with alternatingpayoff functions. It then applies the method to investigate whether staggeredor synchronized wage adjustment will be preferred when more than two wagesetters interact strategically and dynamically. The results suggest that thestrategic benefit provided by staggered wage adjustment is robust with respectto the number of sectors in the economy. [ABSTRACT FROM AUTHOR]