scholarly journals Towards Human-Competitive Game Playing for Complex Board Games with Genetic Programming

Author(s):  
Denis Robilliard ◽  
Cyril Fonlupt
2013 ◽  
Vol 2 (1) ◽  
pp. 175-184
Author(s):  
Samuel Choi Ping Man

Programming computers to play board games against human players has long been used as a measure for the development of artificial intelligence. The standard approach for computer game playing is to search for the best move from a given game state by using minimax search with static evaluation function. The static evaluation function is critical to the game playing performance but its design often relies on human expert players. This paper discusses how temporal differences (TD) learning can be used to construct a static evaluation function through self-playing and evaluates the effects for various parameter settings. The game of Kalah, a non-chance game of moderate complexity, is chosen as a testbed. The empirical result shows that TD learning is particularly promising for constructing a good evaluation function for the end games and can substantially improve the overall game playing performance in learning the entire game.DOI: 10.18495/comengapp.21.175184


2021 ◽  
Vol 19 (1) ◽  
pp. 119-131
Author(s):  
András Ferenc Dukán ◽  
Katalin Fried ◽  
Csaba Szabó
Keyword(s):  

Author(s):  
Tad Gonsalves

The classical area of AI application is the board games. This chapter introduces the two most prominent AI approaches used in developing board game agents – the MinMax algorithm and Machine Learning and explains their usage in playing games like tic-tac-toe, checkers, othello, chess, go, etc., against human opponents. The game tree is essentially a directed graph, where the nodes represent the positions in the game and the edges the moves. Even a simple board game like tic-tac toe (noughts and crosses) has as many as 255,168 leaf nodes in the game tree. Traversing the complete game tree becomes an NP-hard problem. Alpha-beta pruning is used to estimate the short-cuts through the game tree. The board game strategy depends on the evaluation function, which is a heuristic indicating how good the player's current move is in winning the game. Machine learning algorithms try to evolve or learn the agent's game playing strategy based on the evaluation function.


2021 ◽  
Author(s):  
Nicole Charewicz

The present study examined the effects of cooperative and competitive game playing on empathy. Participants were randomly assigned to one of two conditions, with a confederate: playing a video game cooperatively (N = 51), or playing a video game competitively (N = 55). The game played was the non-violent, puzzle-platformer Portal 2. When playing cooperatively, participants completed levels through the multiplayer option where they had to act together with the confederate to be successful. In the competitive condition participants played the single-player campaign and competed with the confederate for the best time-to-completion of the first series of levels. After playing Portal 2 for approximately 15 minutes, participants watched the confederate submerge her hand in what they thought was ice-cold water for 30 seconds. Participants sat facing the confederate and rated their perception of the confederate’s pain, their own pain, the amount of empathy they felt for the confederate, as well as how close they felt to the confederate. A subsequent measure also assessed the extent of participants’ empathic concern by providing them the option to reduce the time that the confederate had to put her hand in the water a second time. Results showed no significant differences between the two conditions with respect to levels of empathy. However, participants felt more trusting and friendly towards the confederate in the cooperative condition.


Author(s):  
Sanna-Mari Tikka ◽  
Marja Kankaanranta ◽  
Tuula Nousiainen ◽  
Mari Hankala

In the context of computer games, learning is an inherent feature of computer game playing. Computer games can be seen as multimodal texts that connect separate means of expression and require new kinds of literacy skills from the readers. In this chapter, the authors consider how the computer-based learning tool Talarius, which enables students to make their own digital games and play them, lends itself to literacy learning. The learning subject is a children’s novel, and thus it is narrative by its nature. In addition, the learning tool provides the potential to interweave narrative contents into the games made by it. The focus of this chapter is on the relationship between narrativity and learning in computer games, in this case, digital board games. The research question is: How do the narrative functions of the learning tool support learning in game creation and game playing?


2021 ◽  
Vol 14 (1) ◽  
pp. 182-187
Author(s):  
Ana JUHÁSZ

Abstract: The usage of games in the process of teaching and learning is always advantageous, because children prefer to learn playfully. Board-games are particularly enjoyable for children. They do not learn consciously, but they enjoy playing together with their parents and siblings, because board-games bring together both family and friends. Playing board-games is not only a joyful activity, it also develops different skills of the player, as communication skills, strategy creating and problem solving competency, cooperation, etc. Nowadays there are many boardgames on sale, active board-game playing communities organize events, and a culture of playing board-games is developing. Thus integrating board-games in educational activities seems to be a natural process to follow. But this integration has many obstacles, as time and curriculum constrains, the lack of methodological knowledge of the teachers, inadequate choose of educational board-games for some subjects, etc. The aim of this research is to study primary school teachers’ attitude to playing board-games and their board-game playing practice. The results show that majority of the participating elementary school teachers love playing boardgames, almost half of them also play board games in their private life. Most of them bring these games to the classroom as well. Teachers love these games, because they are fun, teach logical thinking, make students creative, help them to relax, are team builders, motivate students to learn, get used to speed, develop attention, teach strategies, and are childhood favorites.


2021 ◽  
Author(s):  
Nicole Charewicz

The present study examined the effects of cooperative and competitive game playing on empathy. Participants were randomly assigned to one of two conditions, with a confederate: playing a video game cooperatively (N = 51), or playing a video game competitively (N = 55). The game played was the non-violent, puzzle-platformer Portal 2. When playing cooperatively, participants completed levels through the multiplayer option where they had to act together with the confederate to be successful. In the competitive condition participants played the single-player campaign and competed with the confederate for the best time-to-completion of the first series of levels. After playing Portal 2 for approximately 15 minutes, participants watched the confederate submerge her hand in what they thought was ice-cold water for 30 seconds. Participants sat facing the confederate and rated their perception of the confederate’s pain, their own pain, the amount of empathy they felt for the confederate, as well as how close they felt to the confederate. A subsequent measure also assessed the extent of participants’ empathic concern by providing them the option to reduce the time that the confederate had to put her hand in the water a second time. Results showed no significant differences between the two conditions with respect to levels of empathy. However, participants felt more trusting and friendly towards the confederate in the cooperative condition.


Sign in / Sign up

Export Citation Format

Share Document