Control Game Research Articles

GANs training: A game and stochastic control approach

AbstractTraining generative adversarial networks (GANs) are known to be difficult, especially for financial time series. This paper first analyzes the well‐posedness problem in GANs minimax games and the widely recognized convexity issue in GANs objective functions. It then proposes a stochastic control framework for hyper‐parameters tuning in GANs training. The weak form of dynamic programming principle and the uniqueness and the existence of the value function in the viscosity sense for the corresponding minimax game are established. In particular, explicit forms for the optimal adaptive learning rate and batch size are derived and are shown to depend on the convexity of the objective function, revealing a relation between improper choices of learning rate and explosion in GANs training. Finally, empirical studies demonstrate that training algorithms incorporating this adaptive control approach outperform the standard ADAM method in terms of convergence and robustness. From GANs training perspective, the analysis in this paper provides analytical support for the popular practice of “clipping,” and suggests that the convexity and well‐posedness issues in GANs may be tackled through appropriate choices of hyper‐parameters.

Reinforcement learning-based formation-surrounding control for multiple quadrotor UAVs pursuit-evasion games

This paper proposes a reinforcement learning-based formation-surrounding control method for multiple quadrotor unmanned aerial vehicles (UAVs) pursuit-evasion (MPE) games system subject to external disturbances. In the framework of the MPE games, the pursuers aim to equally surround the evaders which try to avoid being surrounded when forming the desired formation. By constructing position and attitude tracking error subsystems of quadrotor UAV, this paper proposes two control strategies which combines the feedforward control technique and reinforcement learning (RL) method. First, two novel cost functions are presented for the quadrotor UAV with external disturbances. Then, two control schemes based on RL have been developed to guarantee the stability of the tracking error subsystem. Subsequently, two critic-only neural networks (NN) weight update laws that only satisfy finite excitation conditions are proposed to estimate the optimal cost function. Furthermore, Nash equilibrium for multiple quadrotor UAVs is achieved by means of RL strategy to solve the Hamilton-Jacobi-Isaacs (HJI) equations. And the property of equally surrounding is proved for the first time by utilizing Euler's formula in this paper. Finally, the numerical simulation results are given to show the effectiveness and superior performance of the proposed control method.

Design and Implementation of Multi Player Pong Game using Altera DE2 Board

Pong game is a simple but entertaining game of logic control. This research paper presents the design and implementation of an FPGA-based Pong game that runs on an Altera DE2 board using Verilog HDL. This article explains the VGA controller, object creation and animation, and text subsystem and of course how to link them all together to build a functioning circuit. There is an interesting multi-player mode and single-player mode feature in this design scheme. This game's multiplayer mode features both real-time and automatic players to create a competitive atmosphere. This design method followed less complicated, fastest processing, and utilized memory requirements and logic elements. The single-player mode uses 1.3% of total logic elements, the two-player mode uses 1.32%, and automatic player vs. real player uses 1.456% of total logic elements which is very small compared to the other gaming schemes and it reduces the processing time that is cost-effective for universal use. All the modules are designed by using Verilog HDL. The synthesis is done with the help of Altera DE2 FPGA. Functional simulation and synthesis prove that the design is universally usable and combines different modules in one module that presents sound entertainment and extends the electronics application-based work in the future.

Convergence Analysis and Strategy Control of Evolutionary Games With Imitation Rule on Toroidal Grid

Convergence Analysis and Strategy Control of Evolutionary Games With Imitation Rule on Toroidal Grid

Distributed Adaptive Inverse Differential Game Approach to Leader's Behavior Learning for Multiple Autonomous Followers

In this study, the leader's behavior learning problem is investigated for a class of leader-follower systems, where the leader's behavior is assumed not a priori known to all followers that are autonomous. A multi-player nonzero-sum differential game is introduced to indicate the control interaction between agents, where the leader's behavior is modelled by an unknown cost function. The autonomous followers aim to retrieve the weighting matrix in the leader's cost function collaboratively. A distributed online adaptive inverse differential game (IDG) approach to the leader's behavior learning is proposed for the autonomous followers. Specifically, a concurrent learning (CL) based adaptive law and an interactive game controller are first developed for each autonomous follower to learn the leader's feedback gain matrix online, while the feedback Nash equilibrium of the game can be achieved. Then, a linear matrix inequality (LMI) optimization problem is formulated to determine the weighting matrix of the leader's cost function for each autonomous follower. The proposed method simply requires that all followers share their interactive feedback gain matrices, not their private intents, and use only the system state data, not both the system state data and the leader's control input data. The main advantages of the proposed method are that it can be implemented online without requiring the persistent excitation condition and needs less computational power for all followers. Finally, numerical simulations are provided to demonstrate the effectiveness and feasibility of the developed method.

You Got It in Your Hands: Stop-Signal Modality Influences on Reactive Response Inhibition with Gaming Controls

Mastering the art of stopping initiated actions is vital when playing video games. However, what characteristics make up the perfect warning or stop-signal remains unclear. In the present study we compared performance in a basic and a gamified stop-signal task depending on different stop-signal modalities: auditory, haptic and audio-haptic. Data from a complete within-subjects design (N = 24), revealed an advantage of haptic or audio-haptic stop-signals as compared to purely auditory ones. Further, results show an overall slower performance in the game-version compared to the basic version. With regards to the subjective experience, the results revealed higher motivation to perform in the gamified task, but a somewhat deeper flow experience in the basic task. In sum, these results confirm that stop-signal modality influences reactive response inhibition in both basic and gamified tasks. Future research may extend and generalize these findings to other cross-modal and more complicated gaming setups. Game developers may draw on these findings to optimize the communication of stop signals via vibrations in a handheld controller.

Game Application as Teaching Tool to Assist Mastering Installation of Three-Phase Motor Control Topic: Expert Perception

The learning and teaching process using conventional methods might cause students to be unable to highlight their true potential. Besides, it can be more difficult for teachers to choose the types of games that suit the curriculum and students' needs. Hence, this study aims to develop a game application as a teaching assistant tool for a three-phase direct online starter topic in Electrical Technology Malaysian Vocational Certificate subject for Vocational College students using the Android platform. Learning materials and games are developed using multimedia and interactive elements to attract students to be active in using the learning medium based on game applications as 21st-century learning tools. The development purpose of the game application is to give early exposure to students to the installation of three-phase motor control before going through the laboratory session. The behaviorism learning theory and Game development Life Cycle (GDLC) model, were implemented in the game application development in this research. The researcher used Unity 3D software is online software such as Canva and Microsoft PowerPoint design tools interactively to make a game-based learning application for the three-phase motor control installation subject. Based on the analysis of the findings, the experts agreed that the functionality of this three-phase Motor Control game application can be used well and is suitable to be used as a teaching aid. In addition, these research results can be used by teachers to increase students' interest and further make the learning process more interesting to improve student understanding.

Effects of a single bout of mobile action video game play on attentional networks

Background Video game play has been linked to a range of cognitive advantages, and investigations in this domain have predominantly utilized cross-sectional designs or long-term training paradigms. Nevertheless, the specific effects of engaging in a single bout of video game play remain poorly understood. Consequently, the objective of this study is to examine the influence of a single session of mobile action video game (MAVG) play on attentional networks among college students. Methods Seventy-two nonvideo game players were assigned randomly into an MAVG and a control game group. Participants in the MAVG group engaged in a 60-minute session of an action video game played on mobile phones, while the control group played a mobile card game for the same duration. All participants completed the attentional network test (ANT), which assesses alerting, orienting, and executive control network efficiencies, before and after the intervention. Results The MAVG group had significantly improved alerting network efficiency following the intervention, compared to before (p < 0.05); the control game group did not. Neither executive control network efficiency nor orienting network efficiency were found to be improved by the intervention. Conclusion The present data demonstrated that a single bout of MAVG play can improve alerting network efficiency selectively in young-adult college students. MAVGs may be useful for promoting attentional function with the advantages of being accessible virtually any time and anywhere.

83 Efficacy of a Tablet-Based Cognitive Flexibility Intervention in Youth with Executive Function Deficits

Objective:Executive functions (EFs) are considered to be both unitary and diverse functions with common conceptualizations consisting of inhibitory control, working memory, and cognitive flexibility. Current research indicates that these abilities develop along different timelines and that working memory and inhibitory control may be foundational for cognitive flexibility, or the ability to shift attention between tasks or operations. Very few interventions target cognitive flexibility despite its importance for academic or occupational tasks, social skills, problem-solving, and goal-directed behavior in general, and the ability is commonly impaired in individuals with neurodevelopmental disorders (NDDs) such as autism spectrum disorder, attention deficit hyperactivity disorder, and learning disorders. The current study investigated a tablet-based cognitive flexibility intervention, Dino Island (DI), that combines a game-based, process-specific intervention with compensatory metacognitive strategies as delivered by classroom aides within a school setting.Participants and Methods:20 children between ages 6-12 years (x̄ = 10.83 years) with NDDs and identified executive function deficits and their assigned classroom aides (i.e., “interventionists”) were randomly assigned to either DI or an educational game control condition. Interventionists completed a 2-4 hour online training course and a brief, remote Q&A session with the research team, which provided key information for delivering the intervention such as game-play and metacognitive/behavioral strategy instruction. Fidelity checks were conducted weekly. Interventionists were instructed to deliver 14-16 hours of intervention during the school day over 6-8 weeks, divided into 3-4 weekly sessions of 30-60 minutes each. Baseline and post-intervention assessments consisted of cognitive measures of cognitive flexibility (Minnesota Executive Function Scale), working memory (Weschler Intelligence Scales for Children, 4th Edn. Integrated Spatial Span) and parent-completed EF rating scales (Behavior Rating Inventory of Executive Function).Results:Samples sizes were smaller than expected due to COVID-19 related disruptions within schools, so nonparametric analyses were conducted to explore trends in the data. Results of the Mann-Whitney U test indicated that participants within the DI condition made greater gains in cognitive flexibility with a trend towards significance (p = 0.115. After dummy coding for positive change, results also indicated that gains in spatial working memory differed by condition (p = 0.127). Similarly, gains in task monitoring trended towards significant difference by condition.Conclusions:DI, a novel EF intervention, may be beneficial to cognitive flexibility, working memory, and monitoring skills within youth with EF deficits. Though there were many absences and upheavals within the participating schools related to COVID-19, it is promising to see differences in outcomes with such a small sample. This poster will expand upon the current results as well as future directions for the DI intervention.

89 A Pilot Study of a Parent-Delivered Game-Based Cognitive Intervention in Children Born Preterm

Objective:Preterm birth (gestational age < 37 weeks) is associated with delays in the development of executive functions and their precursors, including controlling attention and retaining task-relevant information. In the current study, we aim to examine the potential therapeutic effects of a novel cognitive tablet game, Dino Island (DI), and its implementation through a parent-delivered intervention program on cognitive development in preterm children.Participants and Methods:In total, 34 participants (M = 4.99 years old) were recruited from a perinatal follow-up clinic or through the community in Calgary, AB. Participants were randomly assigned to either the DI intervention (n = 20) or tablet-based educational control games (C; n = 14). Parents completed a 2-hour training program that included information about how to support their child through the intervention using behavioural supports and metacognitive strategies. Neuropsychological assessment was done prior to beginning the intervention and after 12 weeks of intervention. Various tests were used to assess near transfer measures of sustained attention, shifting attention, executive function, verbal working memory and inhibition, and to assess far transfer measures of language skills and early numeracy. Families tracked weekly progress using journals, with the goal of 3-4 30-minute sessions per week. Multiple ANCOVA analyses were run to analyze quantitative data using the pre-test score as a covariate.Results:A total of 21 participants completed the 12 weeks of intervention (DI: n = 11 and C: n = 10). Those who did not complete the intervention withdrew from the study or were unable to make a follow-up assessment due to COVID-19 restrictions. Groups did not significantly differ in age (DI: M = 4.92, C: M = 4.61), sex (DI: Female = 6, C: Female = 6), or in weeks preterm (DI: M = 29.49 weeks, C: M = 32.7 weeks).Multiple ANCOVAs were run to determine the effect of either the DI or Control intervention on the cognitive measures after controlling for the pre-intervention score of participants. As compared to the Control group, the DI intervention group showed near transfer gains in sustained attention (F(1,7) = 5.1, p = 0.043), and executive functions (F(2,18) = 5.41, p = 0.014), as well as far transfer gains in phonetic awareness (F(2,16) = 11.63, p = 0.001), vocabulary and oral language skills (F(2,7) = 5.54, p = 0.014), and number identification fluency (F(2,17) = 11.37, p = 0.001). Detailed analyses will be discussed in the poster.Conclusions:This study provides preliminary support for the potential efficacy of the DI intervention when delivered by parents to children born preterm. Pre-post testing after 12 weeks of intervention indicated both near and far transfer gains. These results highlight the benefits of utilizing a tablet game format to facilitate collaborative parent-child interactions in cognitive intervention. This intervention provides a potential affordable and engaging alternative to existing cognitive interventions. Further investigation with a larger and more diverse sample is required.

Development and Validation of a System for Game Control Based on a Force Plate

A force plate is a device that measures the ground reaction force caused by a shift in the human body’s center of mass (CoM). Using a controlled change in the human body’s CoM, the human body’s center of pressure (CoP) is shifted in a 2D plane, along with an acceleration of the CoM along the plane perpendicular to the force plate, which allows for a generation of reference values for game control. In this paper, the development and validation of a system for game control based on a force plate are described. The game control system consists of a force plate, an electronic board used for measuring and PC communication via USB, and a PC application for data acquisition, system calibration, and game control. Based on the measured values of the player’s CoP and the CoM acceleration along a plane perpendicular to the force plate, the game control system simulates pressing the UP, DOWN, RIGHT, LEFT, and SPACE keyboard keys or moving the mouse and clicking the left mouse button, which allows players to control simple games. A mathematical model has been developed for the game control system which includes running system calibration procedures in the system for each individual player. The mechatronic game control system is described in detail, and experiments were run on said system for the purpose of system validation.

The Cooperative Mean Field Game for Production Control with Sticky Price

The Cooperative Mean Field Game for Production Control with Sticky Price

Collaborative Development and Transportation Volume Regulation Strategy for an Urban Agglomeration

Transportation plays an important role in urban development and the formation of urban agglomerations. Indexes including urban centrality, urban development intensity, and degree of urban development imbalance are defined to measure the level of urban development, and are taken as the basis for transportation regulation within urban agglomerations. Regulation of transportation volume is divided into static and dynamic regulation, and this paper studies static regulation. There are two purposes for static regulation. One is to solve the problems of unbalanced urban development and collaborative development, and the other is to solve the problem of rational utilization of the highway transport network in an urban agglomeration so that the total transportation volume of the urban agglomeration does not exceed the total transportation volume that the transport network can bear, realizing coordinated transport, improving transport efficiency, and reducing traffic congestion and traffic accidents. A distributed intelligent regulation model based on the principle of game control is proposed, which is divided into three layers: macro-regulation (government layer), meso-regulation (urban agglomeration layer), and micro-regulation (individual city game layer). The regulation strategies and methods of the urban agglomeration layer and individual city game layer are given, and are verified and illustrated using as the research object called the Jilin Province urban agglomeration in the northeast of China. The paper contributes to the field by presenting innovative research and provides important theories and methods for collaborative development and transportation within urban agglomerations.

The Interactive Sphere for Three-Dimensional Control in Games and Virtual Reality

In electronic games, the controller is the mean through which the player can interact with the game’s virtual world, being an essential factor in all of the user experience. New controllers may, therefore, completely modify the player experience, also serving as a tool to investigate new ways of interacting with interactive systems of various purposes. In this context, this paper presents the Interactive Sphere, a spherical device to be employed specially with games and virtual reality environments. This novel device combines the pressing of certain regions of the sphere with gestural interaction, in addition to providing haptic, auditive and visual feedback. The paper describes all of the rationale behind the decisions taken during the design and development process of the device, in addition to the techniques employed for implementing the detection of the acts of pressing and moving the Interactive Sphere. In this project, accessible, low-cost materials and techniques were prioritized, which could be more easily adapted to other contexts. We envision that the lessons learned and the guidelines derived from its design and development process may assist in the idealization and construction of new ways of interacting, by providing a set of methods, techniques and technologies that were employed in the development of a new physical artifact of interaction presented in this work.

A Serious Video Game Targeting HIV Testing and Counseling: A Randomized Controlled Trial

PurposeAdolescents are the age group that is least likely to know their HIV status and may unknowingly transmit the virus to others. A randomized controlled trial was conducted to evaluate the impact of the original video game intervention, PlayTest!, on behavioral antecedents for HIV testing and counseling (HTC). MethodsParticipants (N = 287 adolescents) were recruited between 2018 and 2020 and were 48% female, aged 14–18 years (mean age = 15.4 years), and 76% racial minorities. Participants were randomized 1:1 and assigned to either play PlayTest! or a set of control games, ∼one session per week for an hour per session over 4–6 weeks (gameplay) after school. The primary outcome measure was participants' attitudes around HTC at 6 months, with intentions, knowledge, self-efficacy, and behaviors assessed as secondary outcomes. ResultsTwo hundred and ninety-six participants were enrolled/randomized; nine were withdrawn due to incomplete parental consent forms, leaving 287 participants: 145 were randomized to PlayTest! and 142 to the control condition. Mixed between-within subjects ANOVAs assessed the impact of the study conditions on outcomes. Improvements were seen in the PlayTest! group in HTC attitudes (p < .001), intentions (p < .001), knowledge (p < .001), and self-efficacy (p = .002) at all time-points. At 6 months, for those who had access to HTC (N = 134; prior to COVID-19) and for those who did not have access to HTC (N = 261; during COVID-19), there were no differences in self-reported HTC between the two groups (p = .289 and p = .074, respectively). DiscussionPlayTest! impacted important behavioral antecedents related to HTC and has the potential to broadly increase HTC rates in adolescents.

Robust ADP-based control for uncertain nonlinear Stackelberg games

Stackelberg games allow players to access system information differently and take actions asynchronously. This paper introduces a robust adaptive dynamic programming-based method to solve the nonlinear two-player Stackelberg game subject to external disturbances. Combined with a neural network identifier, our method is implemented on the actor–critic-disturbance structure to approximate the optimal value function, i.e., the corresponding Stackelberg equilibrium. With the aid of costate, we transform this leader–follower optimization problem into solving two parametric equations and a costate equation. The coefficients of critic approximators and the costate are updated simultaneously to reach the Stackelberg equilibrium. The proposed control method finds real-time approximations of the Stackelberg-Saddle equilibrium while ensuring the closed-loop system’s stability. Finally, the simulation example shows the effectiveness and advantage of our method.

Exploring the evolutionary game of rumor control based on prospect theory

Exploring the evolutionary game of rumor control based on prospect theory

Microgames and Language Learning: Performance Before Competence?

This paper reports on a study in which pairs of first-graders played microgames on small-screen handheld devices every day for 9 weeks. Its purpose was to find out whether, and if so how, adding digital games into classroom communications could ‘fast-track’ learning, accelerate language and literacy development, and whether it could also help bridge communication barriers for ELL learners, who may be shy, intimidated, or simply linguistically unable to interact as equals with their classmates. The “microgames” students played together were fast-paced, high engagement games that feature almost entirely one-word, verb-based instructions: “Rock”, “Hide”, “Pick”, “Protect”, and so on. Videos, fieldnotes and teacher reports note that social and linguistic interaction between children as and after they played demonstrably increased. Students’ language learning appeared to be accelerated by the game’s imperative to quickly decode and follow written instructions, even though many of these 6- and 7-year-olds did not yet read well enough to do that. The vocabulary which they were, in a matter of days, effectively recognizing and acting on was often far advanced from their usual first grade language arts lexicon, with words like “disguise”, “hypnotize”, “escape” and so on, presumed and treated, from a curricular standpoint, as exceeding their linguistic competence. Equally noteworthy was the technical competence the children displayed in mastering game controls, along with an array of different game mechanics. Using video documentation throughout the study provided both empirical evidence and persuasive examples of how playful interaction with more capable peers can support linguistic development as well as, or even more effectively than, conventional language curriculum and instruction, suggesting that when learning is scaffolded by play, our reach can so often exceed our grasp.

Attitude Takeover Control of Failed Spacecraft via Leader–Followers Adaptive Cooperative Game

In this paper, the problem of microsatellites-based adaptive cooperative game attitude takeover control for a failed spacecraft is investigated. Specifically, a manned microsatellite (leader) and a team of autonomous microsatellites (followers) are ordered to cooperate to complete the attitude control task in an optimal way, in which the control strategy and the cost function (or intent) of the leader are unknown to the followers. Based on the differential game (DG) theory, the microsatellites-based attitude takeover control problem is formulated as a cooperative DG, in which each microsatellite has the individual cost function. A key problem is that the followers must infer the leader’s intent first, that is, retrieve the weighting matrix of the cost function of the leader. To achieve this, a composite adaptive law is introduced for each follower to estimate the feedback gain matrix of the leader by using system state data and the cost functions of other followers; based on this, the leader’s intent is inferred online by minimizing a residual error. Then, the cooperative game control law of each follower is designed by itself, and the Pareto equilibrium of the DG system is achieved. Finally, the effectiveness of the proposed leader–followers adaptive cooperative game control method is verified by a simulation study.

Understanding and addressing smartphone addiction: A multidisciplinary perspective

The present study investigates the escalating dependency on smartphones, with tendencies toward severe addiction, thereby causing detrimental effects on both psychological and physiological well-being. The group addicted to mobile phones exhibits behavioral and neurophysiological differences compared to the non-addicted group. Non-invasive neural modulation techniques such as transcranial direct current stimulation and aerobic exercises such as HPCOSMOS exergaming (Treadmill-based, combining action control and motion perception in a Switch game) may represent cost-effective, adaptable, and promising therapeutic approaches. That will contribute to establishing a theoretical foundation for the rehabilitation and treatment of individuals afflicted with smartphone addiction.