Video Sequence Analysis for On-Table Tennis Player Ranking and Analysis

With the rapidly developing of the scientific research in the field of sports, big data analytics and information science are used to carry out technical and tactical statistical analysis of competition or training videos. The table tennis is a skill oriented sport. The technique and tactics in table tennis are the core factors to win the game. With the endlessly emerging innovative playing techniques and tactics, the players have their own competition styles. According to the competition events among athletes, the athletes’ competition relationship network is constructed and the players’ ranking is established. The ranking can be used to help table tennis players improve daily training and understand their ability. In this paper, the table tennis players’ ranking is established their competition videos and their prestige scores in the table tennis players’ competition relationship network.

A Random Forest approach to identify metrics that best predict match outcome and player ranking in the esport Rocket League

Notational analysis is a popular tool for understanding what constitutes optimal performance in traditional sports. However, this approach has been seldom used in esports. The popular esport “Rocket League” is an ideal candidate for notational analysis due to the availability of an online repository containing data from millions of matches. The purpose of this study was to use Random Forest models to identify in-match metrics that predicted match outcome (performance indicators or “PIs”) and/or in-game player rank (rank indicators or “RIs”). We evaluated match data from 21,588 Rocket League matches involving players from four different ranks. Upon identifying goal difference (GD) as a suitable outcome measure for Rocket League match performance, Random Forest models were used alongside accompanying variable importance methods to identify metrics that were PIs or RIs. We found shots taken, shots conceded, saves made, and time spent goalside of the ball to be the most important PIs, and time spent at supersonic speed, time spent on the ground, shots conceded and time spent goalside of the ball to be the most important RIs. This work is the first to use Random Forest learning algorithms to highlight the most critical PIs and RIs in a prominent esport.

A Random Forest approach to identify metrics that best predict match outcome and player ranking in the esport Rocket League

Notational analysis is a popular tool for understanding what constitutes optimal performance in traditional sports. However, this approach has been seldom used in esports. The popular esport “Rocket League” is an ideal candidate for notational analysis due to the availability of an online repository containing data from millions of matches. The purpose of this study was to use Random Forest models to identify in-match metrics that predicted match outcome (performance indicators or “PIs”) and/or in-game player rank (rank indicators or “RIs”). We evaluated match data from 21,588 Rocket League matches involving players from four different ranks. Upon identifying goal difference (GD) as a suitable outcome measure for Rocket League match performance, Random Forest models were used alongside accompanying variable importance methods to identify metrics that were PIs or RIs. We found shots taken, shots conceded, saves made, and time spent goalside of the ball to be the most important PIs, and time spent at supersonic speed, time spent on the ground, shots conceded and time spent goalside of the ball to be the most important RIs. This work is the first to use Random Forest learning algorithms to highlight the most critical PIs and RIs in a prominent esport.

Identification of Players Ranking in E-Sport

Human activity is moving steadily to virtual reality. More and more, people from all over the world are keen on growing fascination with e-sport. In practice, e-sport is a type of sport in which players compete using computer games. The competitions in games, like FIFA, Dota2, the League of Legends, and Counter-Strike, are prestigious tournaments with a global reach and a budget of millions of dollars. On the other hand, reliable player ranking is a critical issue in both classic and e-sport. For example, the “Golden Ball” is the most valuable prize for an individual football player in the whole football history. Moreover, the entire players’ world wants to know who the best player is. The position of each player in the ranking depends on the assessment of his skills and predispositions. In this paper, we studied identification of players evaluation and ranking obtained using the multiple-criteria decision-making based method called Characteristic Objects METhod (COMET) on the example of the popular game Counter-Strike: Global Offensive (CS: GO). We present a range of advantages of the player evaluation model created using the COMET method and, therefore, prove the practicality of using multi-criteria decision analysis (MCDA) methods to build multi-criteria assessment models in emerging areas of eSports. Thus, we provide a methodical and practical background for building a decision support system engine for the evaluation of players in several eSports.

Inverse Reinforcement Learning for Team Sports: Valuing Actions and Players

A major task of sports analytics is to rank players based on the impact of their actions. Recent methods have applied reinforcement learning (RL) to assess the value of actions from a learned action value or Q-function. A fundamental challenge for estimating action values is that explicit reward signals (goals) are very sparse in many team sports, such as ice hockey and soccer. This paper combines Q-function learning with inverse reinforcement learning (IRL) to provide a novel player ranking method. We treat professional play as expert demonstrations for learning an implicit reward function. Our method alternates single-agent IRL to learn a reward function for multiple agents; we provide a theoretical justification for this procedure. Knowledge transfer is used to combine learned rewards and observed rewards from goals. Empirical evaluation, based on 4.5M play-by-play events in the National Hockey League (NHL), indicates that player ranking using the learned rewards achieves high correlations with standard success measures and temporal consistency throughout a season.

Hierarchical Macro Strategy Model for MOBA Game AI

The next challenge of game AI lies in Real Time Strategy (RTS) games. RTS games provide partially observable gaming environments, where agents interact with one another in an action space much larger than that of GO. Mastering RTS games requires both strong macro strategies and delicate micro level execution. Recently, great progress has been made in micro level execution, while complete solutions for macro strategies are still lacking. In this paper, we propose a novel learning-based Hierarchical Macro Strategy model for mastering MOBA games, a sub-genre of RTS games. Trained by the Hierarchical Macro Strategy model, agents explicitly make macro strategy decisions and further guide their micro level execution. Moreover, each of the agents makes independent strategy decisions, while simultaneously communicating with the allies through leveraging a novel imitated crossagent communication mechanism. We perform comprehensive evaluations on a popular 5v5 Multiplayer Online Battle Arena (MOBA) game. Our 5-AI team achieves a 48% winning rate against human player teams which are ranked top 1% in the player ranking system.