Shinfuseki: Go’s Modern Revolution?

The game of Go is a traditional board game originated in ancient China and has long been viewed as the most challenging of board games for artificial intelligence. In 2016, AlphaGo defeated a human professional player in 19 × 19 game with deep neural networks. The ground-breaking advance in computer Go brought artificial intelligence into public view and raised discussions on how to interact with machines in the future. However, AlphaGo is still a highly intelligent computer program without emotion and personality. This paper presents a novel game design of “Naughty AlphaGo”, which is an emotional Go robot player based on AI algorithm. Result shows that the emotion expression approach based on behavioral and kinematic characteristics can support human players’ perception about the AI player’s emotional states through interaction.

The advent of computers and the World Wide Web diversified the way in which the game of Go is played. While traditional human-to-human play still remains an important form of game play, amateur players, along with some professional players, have shifted the play domain from “off-line” club houses to “on-line” Go servers. Computer Go is an important field of study to develop a software to play Go or a Go engine. In addition to human-to-human play, a Go engine or computer intelligence to play Go adds another axis to play configuration: human-to-computer play and computer-to-computer play. These revolutions in the game of Go happened in an extremely short period of time compared to the history of the game, which is more than 4,000 years. We summarize this unavoidable change for the first time in the literature, to our knowledge, and propose a novel way to interact with the current technological advances. We present the new Human-Machine-Computer-Network Interface concept and our implementation of the machine interface with a robot arm. This Lynxmotion robotic arm named Cheonsoo-I successfully places stones on a board under the proposed architecture.

This chapter describes the research from T2 FS-based MoGoTW system to DyNamic DarkForest (DyNaDF) open platform for human and machine co-learning on Go. A human Go player’s performance could be influenced by some factors, such as the on-the-spot environment as well as physical and mental situations of the day. In the first part, we used a sample of games played against machine to estimate the human’s strength (Lee et al. in IEEE Trans Fuzzy Syst 23(2):400–420, 2015 [1]). The Type-2 Fuzzy Sets (T2 FSs) with parameters optimized by a genetic algorithm for estimating the rank was presented (Lee et al. in IEEE Trans Fuzzy Syst 23(2):400–420, 2015 [1]). The T2 FS-based adaptive linguistic assessment system inferred the human performance and presented the results using the linguistic description (Lee et al. in IEEE Trans Fuzzy Syst 23(2):400–420, 2015 [1]). In March 2016, Google DeepMind challenge match between AlphaGo and Lee Sedol in Korea was a historic achievement for computer Go development. In Jan. 2017, an advanced version of AlphaGo, Master, won 60 games against some top professional Go players. In May 2017, AlphaGo defeated Ke Jie, the top professional Go player, at the Future of Go Summit in China. In second part, we showed the development of computational intelligence (CI) and its relative strength in comparison with human intelligence for the game of Go (Lee et al. in IEEE Comput Intell Mag 11(3):67–72, 2016 [2]). Additionally, we also presented a robotic prediction agent to infer the winning possibility based on the information generated by DarkForest Go engine and to compute the winning possibility based on the partial game situation inferred by FML assessment engine (Lee et al. in FML-based prediction agent and its application to game of Go, 2017 [3]). Moreover, we chose seven games from 60 games to evaluate the performance (Lee et al. in FML-based prediction agent and its application to game of Go, 2017 [3]). In this chapter, we extract the human domain knowledge from Master’s 60 games for giving the desired output. Then, we combine Particle Swarm Optimization (PSO) and FML to learn the knowledge base and further infer the game results of Google AlphaGo in May 2017. The experimental results show that the proposed approach is feasible for the application to human and machine co-learning on Go. In the future, powerful computer Go programs such as AlphaGo are expected to be instrumental in promoting Go education and AI real-world applications.

The game of Go has long been viewed as the most challenging of classic games for artificial intelligence owing to its enormous search space and the difficulty of evaluating board positions and moves. Here we introduce a new approach to computer Go that uses 'value networks' to evaluate board positions and 'policy networks' to select moves. These deep neural networks are trained by a novel combination of supervised learning from human expert games, and reinforcement learning from games of self-play. Without any lookahead search, the neural networks play Go at the level of state-of-the-art Monte Carlo tree search programs that simulate thousands of random games of self-play. We also introduce a new search algorithm that combines Monte Carlo simulation with value and policy networks. Using this search algorithm, our program AlphaGo achieved a 99.8% winning rate against other Go programs, and defeated the human European Go champion by 5 games to 0. This is the first time that a computer program has defeated a human professional player in the full-sized game of Go, a feat previously thought to be at least a decade away.

IntroductionYouth soccer academies are challenged with the constant recruitment process of young talented players to select those who will achieve long-term success as an athlete. Youth soccer academies strive to enhance the physical and technical skill development as well as personality development of talented players because psychological characteristics play a crucial role in players’ future success in their transition to professional soccer. The least mature players and relatively young players may have a greater need to possess superior technical/tactical or psycho-behavioral skills than those relatively older counterparts because of the higher selection rates of early maturing players. Due to RAEs, a significant decrease in the overall quality of professional soccer teams might be observed because of the loss of talent of physically smaller, but psychologically stronger and more versatile relatively young players who possess proper technical and tactical attributes at an early age. The first objective of this study was to examine any possible relationship between RAE and personality constructs. A second objective was to identify factors and effects that can help in the further improvement of talent selection and equal opportunities for elite youth soccer players based on their underlying RAE. The third objective was to consider the impact of RAE on long-term career development.MethodsIn this retrospective observational study, 151 elite youth soccer players between 15 and 18 years of age were first grouped in birth quartiles. Personality constructs were then assessed, using a combination of observations, interviews, and a self-assessment questionnaire. Next competition level after 8 years was evaluated to identify RAEs, differences in personality characteristics and opportunities to reach professional soccer player status between relatively older vs. younger players.ResultsA clear significant RAE was observed for the whole database (Q1 = 38.4% vs. Q4 = 13.9%) with OR of 2.61 (χ2 = 19.46, p < 0.01, r = −0.85). Relatively young players had higher median scores on personality constructs such as self-confidence (p = 0.04), while relatively old players had higher median scores on personality constructs such as team orientation (p = 0.03). In the long term, more players of the youngest birth quartile were signed as professional players (76.2%), compared with relatively old players (46.6%). 65.0% of the 20 players had the highest total score on personality constructs developed as a professional soccer player, vs. 35.0% of the 20 players with the lowest scores.DiscussionIn conclusion, this study showed not only further evidence of the RAE but also provided evidence supporting “the underdog hypothesis” in national elite youth teams. Relatively young players were also more likely to get higher value senior professional contracts in the long term. We propose that this may be due to the relatively young players developing superior psychological skills and technical expertise to compensate for their early physical disadvantage. This in turn suggests the need for greater awareness of the importance of personality constructs in the future development of youth elite soccer players. Therefore, the crux of the issue is how youth soccer academies elicit the “best of both worlds” ie. moderating RAE whilst also gaining the benefits of the underdog hypothesis by creating the right environment for every player to develop to their full potential in elite youth soccer academies.

This paper presents the recent technical advances in Monte Carlo tree search (MCTS) for the game of Go, shows the many similarities and the rare differences between the current best programs, and reports the results of the Computer Go event organized at the 2009 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE2009), in which four main Go programs played against top level humans. We see that in 9 × 9, computers are very close to the best human level, and can be improved easily for the opening book; whereas in 19 × 19, handicap 7 is not enough for the computers to win against top level professional players, due to some clearly understood (but not solved) weaknesses of the current algorithms. Applications far from the game of Go are also cited. Importantly, the first ever win of a computer against a 9th Dan professional player in 9 × 9 Go occurred in this event.

Bidaurrazaga-Letona, I, Lekue, JA, Amado, M, and Gil, SM. Progression in youth soccer: Selection and identification in youth soccer players aged 13-15 years. J Strength Cond Res 33(9): 2548-2558, 2019-The aim of this study was to identify the factors that are important for the identification and selection of young soccer players. Ninety-four adolescent soccer players from the under-13 (U13; age = 12.3 ± 0.3 years; n = 50) and under-15 (U15; age = 14.0 ± 0.2 years; n = 44) categories belonging to a professional club participated in the study. Anthropometric measurements, physical tests (sprint, agility, endurance and jump), and maturity status (age at peak height velocity) were recorded over 4 seasons. Comparisons were performed among new players joining the club (Enter players, n = 15), players progressing to the next age category (Club players, n = 54), and players leaving the club (Deselected players, n = 25). A 2-way repeated measures analysis of variance (ANOVA) was performed to determine if significant differences existed between groups and testing time. Better physical performance and improvements observed during the season in performance were found to be one of the main factors for U13 players to continue in the club (p < 0.05-0.001). In the U15 group, although body size, maturation and physical performance appeared to be the most important characteristics for being identified to play in the club (p < 0.05), Club players demonstrated better improvements during the season (p < 0.05). Overall, these results indicate that the identification or promotion of players by coaches depends on indicators which are age-dependent. Therefore, this study has shown that the talent identification program was more a selection process than a promotion process, selecting and identifying a posteriori rather than a priori.

How does information infrastructure shape long-term cultural evolution? Using over four centuries of professional game records from the game of Go, this study explores how strategic dynamics in opening moves reflect historical shifts in the ‘infostructure’ of skilled Go players. Drawing from recent work on how population size, AI, and information technology affect cultural evolution and innovation dynamics, I analyze over 118,000 games using measures of cultural diversity, divergence, and player network composition. The results show distinct eras of collective innovation and homogenization, including an early 20th-century explosion of novel opening strategies, a Cold-War-era die-off, and a recent increase in evolutionary tempo with the arrival of the internet and superhuman AI programmes like AlphaGo. Player population size shows an inverse-U relationship with opening move diversity, and a recent decline in strategic diversity has accompanied a shift in the player network, from many small subgroups to a few large ones. Surprisingly, the influence of AI has produced only a modest, short-lived disruption in the distribution of opening moves, suggesting convergence between humans and AI and incremental rather than revolutionary cultural change.

We investigate the problem of learning to predict moves in the board game of Go from game records of expert players. In particular, we obtain a probability distribution over legal moves for professional play in a given position. This distribution has numerous applications in computer Go, including serving as an efficient stand-alone Go player. It would also be effective as a move selector and move sorter for game tree search and as a training tool for Go players. Our method has two major components: a) a pattern extraction scheme for efficiently harvesting patterns of given size and shape from expert game records and b) a Bayesian learning algorithm (in two variants) that learns a distribution over the values of a move given a board position based on the local pattern context. The system is trained on 181,000 expert games and shows excellent prediction performance as indicated by its ability to perfectly predict the moves made by professional Go players in 34% of test positions.

The game of Go, also called Weiqi or Baduk, is one of the most sophisticated board games in the world. The players compete with each other by surrounding more territory using their stones. There are three phases in a game of Go, including the opening, middle, and endgame. Only a very few psychological studies have investigated the underlying processes or neural mechanisms used while playing Go. It has been suggested that some cognitive abilities may be important during the game, but the recruitment of different kinds of cognitive abilities in three phases is still unknown. The present study addressed this issue by combining experimental psychology approaches and artificial intelligence (AI) algorithms. Twenty-four Go players tried their best to quickly answer 48 Go questions in each of three phases, with different cognitive interference tasks appearing simultaneously. Their accuracy and reaction time on these questions were recorded as their performance. The Go questions were designed and organized by a professional Go player, and some basic requirements for psychological experiments were met. In addition to a control task, there were three types of interference tasks: a visual spatial search, logical reasoning, and calculation. The results showed that the spatial interference task decreased the accuracy in the opening phase, suggesting that spatial ability is the most important cognitive ability used in the opening of a Go game. The logical reasoning interference task decreased the accuracy in the middle and endgame phases, implying that reasoning ability is very critical in these phases. The calculation task had a less significant interference effect. In addition, we used three AI-related algorithms to classify the subjects' performance in the three phases of Go questions under different degrees of cognitive interference. The results showed that these algorithms had much better than chance accuracy to correctly classify the performance in three different phases of Go questions or under different degrees of cognitive interference. Cross validation procedures ensured the generalizability, and permutation tests also indicated that the predictive accuracy of these models was statistically significant. We thus argue that there are indeed different cognitive representations in these three phases under different levels of interference. In summary, in the present study, an experimental approach was adopted to reveal the involvement of cognitive abilities in three phases of Go. In addition, we provide a new perspective for experimental psychology by introducing an AI-related analysis of multivariate data, which infers that artificial intelligence can have a greater influence and make a greater contribution to the understanding of psychology and human intelligence.

This chapter presents a developed fuzzy ontology model for computer Go applications. Unlike previous research, this chapter employs features derived from professional Go players’ domain knowledge to transform them into the opening book sequence and to represent them by a fuzzy ontology for the game of Go. Afterward, the domain experts validate the built fuzzy ontology. The developed fuzzy ontology has been verified through the invited games for Go programs playing against human Go players. The results show that the fuzzy ontology can work for computer Go application.

Introduced in 2016 as a watershed moment in AI development, the announcement of AlphaGo – the first AI system to beat a human professional in the board game of go – garnered a range of mass publicity, and this media coverage often forms the core of scholarly analysis, too. Drawing on a novel dataset of online discussions by professional and amateur players from 2016-2020 which covers the introduction and retirement of AlphaGo, as well as the construction of alternative systems, I outline a new perspective of the impact of the system on the playing community. Moving beyond recognition of audience-centric responses of enchantment/disenchantment by these players, I articulate a process of engagement through which meaning-making and reconstruction occurred within the go community. These findings emphasize the importance of including multiple perspectives in analysis and draws attention to the influence of impacted constituencies in AI construction.

The level of computer programs has now reached professional strength for many games, even for the game of Go recently. A more difficult task for computer intelligence now is to create a program able to coach human players, so that they can improve their play. In this paper, we propose a method to detect and label the bad moves of human players for the game of Go. This task is challenging because even strong human players only agree at a rate of around 50% about which moves should be considered as bad. We use supervised learning with features largely available in many Go programs, and we obtain an identification level close to the one observed between strong human players. Also, an evaluation by a professional player shows that our method is already useful for intermediate-level players.

While VO2max has been widely investigated, there is few research on anaerobic capacity (AC) in soccer players. Previous studies reported that AC is age-dependent and that young individuals had lower AC compared with adults. Thus, we wondered whether AC would have proven more useful than VO2max in differentiating adult soccer players from young players. A total of 37 male athletes from a professional team were recruited and divided into two sub-groups: the adult (AD, n = 20) group, older than 19 years, and the young (YO, n = 17) group, ranged from 16 to 18 years. Each participant underwent an incremental test on a treadmill to assess maximal velocity (Vmax), anaerobic threshold (AT) and VO2max and a supramaximal exercise at a velocity 10 % higher than Vmax to measure AC. The AD group reached higher AT and VO2max with respect to the YO group (55.23 ± 4.65 vs. 51.48 ± 4.73 mL min−1 kg−1), whereas no difference was found in parameters related to the AC. In conclusion, young soccer players had the same AC as adult, but they displayed a lower VO2max. These findings indicated that AC in professional players is fully developed already when they are young while aerobic capacity is still to be developed.

The migration of soccer players has increased in recent years. In this study, we examined the experiences of elite young soccer players as they engaged in a migratory transition from their home country to an English Premier League (EPL) club. Five young players, who made the migratory transition between the ages of 16 and 24, were interviewed. Data were analysed using the principles of content analysis. Verbatim text was then aligned to the emergent themes. Results indicate that young migratory players face the initial frenzy that is associated with an approach from an EPL club before going through a “decision” phase, followed by a period of “migration” and “acculturation” before establishing (or not) their “home from home”. The challenges of leaving home and family while trying to establish themselves as a professional player in an environment that (still) appears to be beset with (traditional) English soccer culture (i.e. high tempo, ruthless, macho, and aggressive) are recounted. While the player's family was a significant source of social support, there is still a need for qualified personnel (e.g. sports psychologists) and/or appropriately trained international recruitment staff and football agents (i.e. in areas of social, psychological, and/or performance lifestyle) to support young players through their migratory transition.