Actions Of Players Research Articles

Designing Procedurally Generated Levels

There is an increasing demand to improve the procedural generation of game levels. Our approach empowers game designers to author and control level generators, by expressing gameplay-related design constraints. Graph grammars, resulting from these designer-expressed constraints, can generate sequences of desired player actions as well as their associated target content. These action graphs are used to determine layouts and content for game levels. We showcase this approach with a case study on a dungeon crawler game. Results allow us to conclude that our control mechanisms are both expressive and powerful, effectively supporting designers to procedurally generate levels.

Open Problem: Reusable Gameplay Trace Samplers

We identify an open problem in game design assistance and automation: the development of reusable gameplay trace samplers. Inside many sophisticated content generators and design tools is a component that samples interesting and plausible sequences of player actions. Details and summary properties of these samples are used to assess generated content and to inform designers. As the development of this component is technically involved (sometimes comparable to making a second implementation of a game's mechanics), design tools often either make use of entirely custom, game-specific samplers or make due without the ability to sample interesting traces at all. This severely limits the population who could benefit from automation to those who are motivated to develop it for themselves. We propose the development of reusable samplers to ease the development of future design automation tools. This paper reviews several systems that demonstrate the availability of technology required by these samplers and the range of applications they may serve. It also sketches how future samplers might be architected. This proposal identifies one way for technical research to make progress on design automation challenges without making problematic assumptions about the nature of player behavior or designer intent. Filling in this missing infrastructure, we claim, will make the use of artificial intelligence in the design process more accessible and thus accelerate game design projects.

The General Mediation Engine

The General Mediation Engine is an architecture for producing game experiences with world mechanics drawn from a planning domain and problem. The system models possible player actions, state updates, and system responses in a graph representation derived from planner input. Paired with an interface that displays state and action information to the player, GME structures gameplay as an on-line expansion of its graph representation.

Simulating Player Behavior for Data-Driven Interactive Narrative Personalization

Data-driven approaches to interactive narrative personalization show significant promise for applications in entertainment, training, and education. A common feature of data-driven interactive narrative planning methods is that an enormous amount of training data is required, which is rarely available and expensive to collect from observations of human players. An alternative approach to obtaining data is to generate synthetic data from simulated players. In this paper, we present a long short-term memory (LSTM) neural network framework for simulating players to train data-driven interactive narrative planners. By leveraging a small amount of previously collected human player interaction data, we devise a generative player simulation model. A multi-task neural network architecture is proposed to estimate player actions and experiential outcomes from a single model. Empirical results demonstrate that the bipartite LSTM network produces the better-performing player action prediction models than several baseline techniques, and the multi-task LSTM derives comparable player outcome prediction models within a shorter training time. We also find that synthetic data from the player simulation model contributes to training more effective interactive narrative planners than raw human player data alone.

Analyzing Stealth Games with Distractions

The ability to distract opponents is a key mechanic in many stealth games. Existing search-based approaches to stealth analysis, however, focus entirely on solving the non-detection problem, for which they rely on static, ahead-of-time models of guard movements that do not depend on player interaction. In this work we extend and optimize an approach based on heuristic search of stealth games to model variation in guard paths as dynamically triggered by player actions. Our design is expressive, accommodating different distraction designs, including remote activation and time delays. Using a Unity3D implementation, we show our enhanced search can solve distraction puzzles found in real games, as well as more complex, multiple-distraction level designs. Our work shows how heuristic search can be applied to dynamically determined contexts, and significantly extends the ability to model and solve stealth games.

STARDATA: A StarCraft AI Research Dataset

We release a dataset of 65646 StarCraft replays that contains 1535 million frames and 496 million player actions. We provide full game state data along with the original replays that can be viewed in StarCraft. The game state data was recorded every 3 frames which ensures suitability for a wide variety of machine learning tasks such as strategy classification, inverse reinforcement learning, imitation learning, forward modeling, partial information extraction, and others. We use TorchCraft to extract and store the data, which standardizes the data format for both reading from replays and reading directly from the game. Furthermore, the data can be used on different operating systems and platforms. The dataset contains valid, non-corrupted replays only and its quality and diversity was ensured by a number of heuristics. We illustrate the diversity of the data with various statistics and provide examples of tasks that benefit from the dataset.

Reputation Systems for Non-Player Character Interactions Based on Player Actions

In digital games there is an emphasis on the idea of quest completion; by completing a quest the character wins resources from the giver of the quest, they also will gain a reputation among the Non-Player Characters (NPCs) for its completion. However, this reputation currently propagates across the game world in an unrealistic manner; many NPCs will know of a completion of a quest many townships over without a narrative rationale. In this paper, we examine a method for allowing NPC interactions to spread reputation in a game world from an initial witness point of a quest completion to all other NPCs. This model is examined in a series of connected graphs: size five models, small world graphs, and graphs developed from digital games. Tests show that propagation of the information is highly dependent upon easily established properties of interactions, such as the graph regularity, average degree, and diameter. Further, real game graphs demonstrate that information generated in high population hubs can be propagated faster than that generated in smaller quests from outlying areas.

Unsupervised Text Classification for Natural Language Interactive Narratives

Natural language interactive narratives are a variant of traditional branching storylines where player actions are expressed in natural language rather than by selecting among choices. Previous efforts have handled the richness of natural language input using machine learning technologies for text classification, bootstrapping supervised machine learning approaches with human-in-the-loop data acquisition or by using expected player input as fake training data. This paper explores a third alternative, where unsupervised text classifiers are used to automatically route player input to the most appropriate storyline branch. We describe the Data-driven Interactive Narrative Engine (DINE), a web-based tool for authoring and deploying natural language interactive narratives. To compare the performance of different algorithms for unsupervised text classification, we collected thousands of user inputs from hundreds of crowdsourced participants playing 25 different scenarios, and hand-annotated them to create a gold-standard test set. Through comparative evaluations, we identified an unsupervised algorithm for narrative text classification that approaches the performance of supervised text classification algorithms. We discuss how this technology supports authors in the rapid creation and deployment of interactive narrative experiences, with authorial burdens similar to that of traditional branching storylines.

Interactive Narrative Intervention Alibis through Domain Revision

Interactive narrative systems produce branching story experiences for a human user using an interactive world. A class of interactive narrative systems, called strong story systems, manage a user's experience by manipulating the interactive world and its characters according to a formal story model. In these systems, a human user may place the world into a state such that the formal story model can no longer control interaction. One solution to this problem, called intervention, is to exchange the undesirable outcomes of a player's action for a set that do not violate the story model. However, the player may become aware that their intended action is being intervened against by a context-sensitive, meta-narrative process. In this paper we describe a method of ensuring game world alibis for interventions through domain modification of world mechanics.

Keeping the Player on an Emotional Trajectory in Interactive Storytelling

Artificial Intelligence (AI) techniques have been widely used in video games to control non-playable characters. More recently, AI has been applied to automated story generation with the objective of managing the player's experience in an interactive narrative. Such AI experience managers can generate and adapt narrative dynamically, often in response to the player's in-game actions. We implement and evaluate a recently proposed AI experience manager, PACE, which predicts the player's emotional response to a narrative event and uses such predictions to shape the narrative to keep the player on an author-supplied target emotional curve.

Symbolic Plan Recognition in Interactive Narrative Environments

Interactive narratives suffer from the narrative paradox: the tension that exists between providing a coherent narrative experience and allowing a player free reign over what she can manipulate in the environment. Knowing what actions a player in such an environment intends to carry out would help in managing the narrative paradox, since it would allow us to anticipate potential threats to the intended narrative experience and potentially mediate or eliminate them. The process of observing player actions and attempting to come up with an explanation for those actions (i.e. the plan that the player is trying to carry out) is the problem of plan recognition. We adopt the framing of narratives as plans and leverage recent advances that cast plan recognition as planning to develop a symbolic plan recognition system as a proof-of-concept model of a player's reasoning in an interactive narrative environment. In this paper we outline the system architecture, report on performance metrics that demonstrate adequate performance for non-trivial domains, and discuss the implications of treating players as plan recognizers.

Story beats in videogames as value-driven choice-based unit operations

We present a framework of story beats, defined as microunits of dramatic action, as a tool for the ludonarrative analysis of videogames. First, we explain the Goal - Action - Reaction - Outcome model of the story beat. Then, we present six types of story beats, Action, Interaction, Inaction, Mental, Emotion, and Sensory, providing videogame examples for each category. In the second half of the paper, we contextualise this framework in the classic game studies theory of videogame narrative and player action: unit operations, gamic action, anatomy of choice, and game design patterns, wrapping it up in the most recent trends in cognitive narratology. Ultimately, we present the story beat as a ludonarrative unit, working simultaneously as a ‘unit operation’ in the study of games as systems, and as a microunit of character action in narrative analysis. The conclusion outlines prospective directions for using story beats in formal, experiential, and cultural game research.

Anterior cruciate ligament injury in elite football players: video analysis of 128 cases.

The purpose of this study was to evaluate with video analysis the circumstances and the mechanism leading to ACL injury in a high-level population of athletes participating in the main European football championships. Video analysis of 128 competitive matches with ACL injury events was performed through Wyscout.com® from August 2009 to January 2020. Details regarding situation, events and injured players were obtained. The type of trauma was assessed on the basis of the game phase, player's action, traumatic mechanism, type of maneuver, contact type, speed of the action and the position of the center of gravity. Of the injuries, 67.2% occurred without direct contact (39.1% non-contact and 28.1% indirect contact) and more than 50% occurred in the first 30 minutes of the match; 31.2% of injuries occurred during ball recovery and 63% in the offensive half; 62.5% of the trauma occurred in a valgus-external rotation maneuver and 35.1% during a deceleration phase with an eccentric contraction of the quadriceps. The referee whistled a foul in 20.6% of cases. Video-analysis may be helpful either to better understand the situations leading to ACL injury or to set up preventive strategies in order to reduce ACL injury in football. Most of the injuries occur during the first thirty minutes after entering the field. It therefore seems unlikely that fatigue will play an important role. Valgus external rotation, eccentric muscular contraction, loss of the center of gravity, attempting to recover the ball are the most frequent scenario.

Stochastic Superiority Equilibrium in Game Theory

The definition of best response for a player in the Nash equilibrium is based on maximizing the expected utility given the strategy of the rest of the players in a game. In this work, we consider stochastic games, that is, games with random payoffs, in which a finite number of players engage only once or at most a limited number of times. In such games, players may choose to deviate from maximizing their expected utility. This is because maximizing expected utility strategy does not address the uncertainty in payoffs. We instead define a new notion of a stochastic superiority best response. This notion of best response results in a stochastic superiority equilibrium in which players choose to play the strategy that maximizes the probability of them being rewarded the most in a single round of the game rather than maximizing the expected received reward, subject to the actions of other players. We prove the stochastic superiority equilibrium to exist in all finite games, that is, games with a finite number of players and actions, and numerically compare its performance to Nash equilibrium in finite-time stochastic games. In certain cases, we show the payoff under the stochastic superiority equilibrium is 70% likely to be higher than the payoff under Nash equilibrium.

Bottom-up reconstitution of focal adhesion complexes.

Focal adhesions (FA) are large macromolecular assemblies relevant for various cellular and pathological events such as migration, polarization, and metastatic cancer formation. At FA sites at the migrating periphery of a cell, hundreds of players gather and form a network to respond to extra cellular stimuli transmitted by the integrin receptor, the most upstream component within a cell, initiating the FA signaling pathway. Numerous cellular experiments have been performed to understand the FA architecture and functions; however, their intricate network formation hampers unraveling the precise molecular actions of individual players. Here, in vitro bottom‐up reconstitution presents an advantageous approach for elucidating the FA machinery and the hierarchical crosstalk of involved cellular players.

Application Algorithms for Basketball Training Based on Big Data and Internet of Things

In recent years, the increasing demand for physical health promotes the basketball sports industry’s reform. The latest science and technology enter the sports industry one after another and constantly impact the traditional sports equipment. However, the conventional sports technology scheme is unreasonable, and the sports training management models are obsolete. So, it is impossible to use scientific methods in basketball training, and the overall training effect is not good. This paper proposes a basketball training algorithm using big data and the Internet of Things. The proposed algorithm uses gesture recognition from continuous video movement characteristics of key figures, trajectory characteristics, and background information fusion. It improves the recognition mechanism based on the Shuangliu C3D video basketball player action classification method. Due to the lack of a scientific exercise plan for basketball players, a training plan based on BMI and IoT-enabled big data is devised. The proposed scheme is implemented so that different basketball players customize their own scientific sports training modules.

Features of physical and technical-tactical preparedness of young football goalkeepers 13-14 years old

The research results of the physical development level, indicators of technical and tactical actions of young football players aged 13–14 of different game roles are presented. The research involved 46 young players aged 13-14 of FC "Arsenal" in Kharkov, including 6 goalkeepers, 8 central defenders, 8 wing defenders, 8 central midfielders, 8 wing midfielders, 8 forwards. The following methods were used: theoretical analysis and generalization of scientific and methodological literature, pedagogical testing, and mathematical statistics. Quantitative indicators of motor actions of young football players of 13-14 years of different game role according to the results of 10 calendar games are determined. It was established that the quality of performance of technical and tactical actions of young football players was not the same for players of different game roles. Goalkeepers mainly make long and short passes (29.8 ± 1.19 and 27.2 ± 1.16% of the total number of technical and tactical actions). The largest number of movements with the back forward, cross step and additional step was made by the goalkeeper (12.3; 7.0; 2.6% of game actions per game), which were statistically significantly higher in relation to all field players (p <0.001). Goalkeepers during the game perform more jumps (32.4 ± 1.48% of all motor actions) and throwing the ball (26.4 ± 1.48%). Goalkeepers’ indicators of speed and power capabilities (in the test "vertical jumping") were statistically significantly superior (p <0.05) to players of all other lines. The correlations between the test indicators that reflect the level of goalkeepers’ physical fitness were determined. A statistically significant correlation was established between the indicator "vertical jumping" and running 30 m (ρ = -0.82, p <0.05), indicators of starting and distance speed (ρ = 0.84 and ρ = 0.86, p <0.05), the indicator "running 10 m on the move" with a 6-minute run, which characterized the overall endurance (ρ = -0.83, p <0.05). Goalkeepers are characterized by the relationship between all technical and tactical actions of the game and the level of motor skills development, namely the statistical significance of the correlation of speed and speed-power qualities with technical and tactical indicators.

NPU RGBD Dataset and a Feature-Enhanced LSTM-DGCN Method for Action Recognition of Basketball Players+

Computer vision-based action recognition of basketball players in basketball training and competition has gradually become a research hotspot. However, owing to the complex technical action, diverse background, and limb occlusion, it remains a challenging task without effective solutions or public dataset benchmarks. In this study, we defined 32 kinds of atomic actions covering most of the complex actions for basketball players and built the dataset NPU RGB+D (a large scale dataset of basketball action recognition with RGB image data and Depth data captured in Northwestern Polytechnical University) for 12 kinds of actions of 10 professional basketball players with 2169 RGB+D videos and 75 thousand frames, including RGB frame sequences, depth maps, and skeleton coordinates. Through extracting the spatial features of the distances and angles between the joint points of basketball players, we created a new feature-enhanced skeleton-based method called LSTM-DGCN for basketball player action recognition based on the deep graph convolutional network (DGCN) and long short-term memory (LSTM) methods. Many advanced action recognition methods were evaluated on our dataset and compared with our proposed method. The experimental results show that the NPU RGB+D dataset is very competitive with the current action recognition algorithms and that our LSTM-DGCN outperforms the state-of-the-art action recognition methods in various evaluation criteria on our dataset. Our action classifications and this NPU RGB+D dataset are valuable for basketball player action recognition techniques. The feature-enhanced LSTM-DGCN has a more accurate action recognition effect, which improves the motion expression ability of the skeleton data.

Organizing a training process of school football class for children of elementary school age

The relevance of the problem under research is determined by the fact that the modern physical education of children of elementary school age requires an efficiency improvement. The schools’ physical education curriculum is aimed at utilization of general forms of physical activity during the day (such as morning gymnastics, athletic pauses, therapeutic exercise, walks, etc.), but the substantial content of these forms of physical activity does not allow for full accounting of the abilities of children of this age group and does not facilitate the efficient development of most physical qualities. The purpose of this article is to elaborate a method to improve football techniques by developing the selected fundamental elements. This article presents a special set of exercises for young football players to help them master the techniques for faster and finer results in less time. The proposed exercises for training process were aimed at perfecting of fundamental technical actions of football players: individual – shots on target, dribbling; and team actions – passing the ball on the run. The materials of this article may be found useful by physical education students, physical education teachers of general schools, secondary and higher educational institutions, as well as by teacher of vocational education.

Extension Agents’ Perceptions of the Role of Extension Services in Organic Agriculture: A Case Study from Saudi Arabia

Extension services (ES) play a crucial role in addressing the various needs of organic farmers and little is known about the extension agents’ (EA’s) perceptions of organic agriculture and the role of ES in organic agriculture. This study investigated EA’s perceptions of the role of ES in organic agriculture. Data were collected via a questionnaire, which was sent electronically to all enlisted extension agents in Riyadh Region, Saudi Arabia. In total, 69 extension agents completed the questionnaire, representing a 54% response rate. Overall, extension agents had slightly positive attitudes toward organic farming but were unsure about their role and participation in this. Furthermore, their perceptions of the role of ES in organic agriculture significantly varied according to their age, work experience in organic agriculture, and education level. These findings have implications for the design of future training programs for the professional development of extension agents and will enable planners, policy makers, and related ministries to devise viable and workable policies and plans that truly reflect the concerns and challenges of extension agents and consider the skills of extension agents that need to be improved. This research will also have positive implications for the national organic agriculture policy, as it provides research-based information on the actual players in the farming systems of Saudi Arabia.