December 28, 2016 at 18:09How artificial intelligence shapes the future of interactive games
- Transfer
Today, on the blog of the Management of Internet Game Projects program , we have prepared and translated for you an article written by Kill Screen editor-in-chief Zack Bajor on artificial intelligence using the example of The Suspect and the movie She .
In the movie “She” (2013), the protagonist Theodore plays a game where he comes across a crazy swearing cartoon character with artificial intelligence. A little foul-speaking alien enters into a conversation with Theodore, remaining stubbornly useless. Realizing that this can be a test, Theodore curses him in response, a verbal skirmish ensues, at the end of which the alien shows Theodore the next path.
“She” is science fiction, but interactive games like in this film may soon become reality. The Alien Child game, created by David O'Reilly, gives some insight into how artificial intelligence (AI) and machine learning can make future games more fun and interactive than ever.
“The most fascinating thing about using machine learning is that AI is studying us, just as it is studying itself and what we are writing to it,” says Guy Gadney, director of the interactive thriller with AI “The Suspect”.
The Suspect uses machine learning in the conversation of players with fictitious criminal Marcus Winter. To save the people he holds hostage, players need to use interrogation tactics in an attempt to outwit the criminal.
As in interaction with the chat bot, players respond to Winter with text messages to which the AI responds on the fly. With the goal of achieving a sense of natural conversation with elements of guile, similar to that depicted in the movie “She,” Gadney uses machine learning to create natural saturation and tension. “We wanted to achieve this surprise, which only happens when the car goes beyond common sense and creates a situation that no one expected ,” he says. “As humans, we tend to share information. It makes everything very believable . ”
Software in the traditional sense is a set of strict rules that are respected by the machine to the letter. Typically, a computer only executes a chain of commands, but machine learning allows the computer to identify rules over time and experiment. “Machine learning is defined as a class of programs in which performance improves over time ,” explains Pradeep Dubey, Intel Fellow and Director of Parallel Computing Lab. “The more data the system consumes, the better it gets.”
George Dolbier, Technical Director of IBM Interactive Media in North America, describes machine learning as “a way to write software not with code, but with data . ” “The program makes its choice, performs actions based on statistics and changes behavior based on new data, ” he says.
Due to its flexibility, machine learning and AI technologies open up a whole world of new creative possibilities, says Dolbier. They can be applied.“In almost all aspects of the gaming experience in the future, for example, in decisions on how to adjust the level of difficulty and the reward system for special players, by analyzing large amounts of player data or in creating completely fictional characters with whom we can interact ,” he says.
In May, for example, SethBling, a YouTube blogger, wrote a program called MarI / O that learned to play Super Mario World (1990) . Unlike other AIs, she started without preliminary instructions, and learned to pass the level like ordinary players: trial and error. MarI / O did not have to “think” how to get through the game. After each death, she repeated successful actions and tried random ways to avoid failure. Despite being close to human abilities, the MarI / O machine way of thinking remained obvious due to her focus on achieving her final goal, ignoring temptations such as bonuses and coins along the way - a human player would most likely not lead yourself in a similar way.
Machine learning may not yet be ready to fully reproduce human behavior, but Gadney believes that it can bring more human into people's interactions with technology. “As we grow, we learn the world through emotions and experience,” he explains. “And if we can use machine learning to reproduce this experience and make it interactive, I think we are doing what we need . ” The uniqueness of The Suspect lies in machine learning, but this does not mean that the game writes itself or that the plot is arbitrary. It has been used in combination with other, more traditional forms of game design.
Gadney says it's best to take it nowmachine learning in game design as another tool, like a brush. This tool is far from perfect. In March, Microsoft's Twitter bot, Tay, was supposed to learn how to conduct informal conversations with those who interact with it. But after 24 hours of directional trolling , she began to hate everyone and cast curses, and was turned off. This case proves the need to strike a balance between freedom and certain rules. Such as taking into account the existence of trolls on the forums.
It is likely that one day machine learning will become as flawless and individual as it was shown in the movie “She . ” Today's games are far from that, but according to the creator of Alien Child, David O'Reilly, a whole new world is opening in front of us, in which players can talk and build more natural relationships with AI. Machines will give odds to human intelligence, says Dubey. “Now this is not just a theory. In practice, cars sometimes show much more accurate results than the best of people . ”
On this happy note, we congratulate everyone on the upcoming New Year, see what new things will bring us in the new year. Well, we hope to please you with interesting translations in the new year. Subscribe to the blog. And also at the beginning of 2017, we can meet with you personally at our open events: the open door day on educational programs of the gaming industry on January 25 and at our conference on creating games on February 11. Admission is free everywhere, only by registration. Do not forget to go through it.
If you have questions, write them in the comments, I will be glad to discuss.
How artificial intelligence shapes the future of interactive games.
Link to the original.In the movie “She” (2013), the protagonist Theodore plays a game where he comes across a crazy swearing cartoon character with artificial intelligence. A little foul-speaking alien enters into a conversation with Theodore, remaining stubbornly useless. Realizing that this can be a test, Theodore curses him in response, a verbal skirmish ensues, at the end of which the alien shows Theodore the next path.
“She” is science fiction, but interactive games like in this film may soon become reality. The Alien Child game, created by David O'Reilly, gives some insight into how artificial intelligence (AI) and machine learning can make future games more fun and interactive than ever.
“The most fascinating thing about using machine learning is that AI is studying us, just as it is studying itself and what we are writing to it,” says Guy Gadney, director of the interactive thriller with AI “The Suspect”.
The Suspect uses machine learning in the conversation of players with fictitious criminal Marcus Winter. To save the people he holds hostage, players need to use interrogation tactics in an attempt to outwit the criminal.
As in interaction with the chat bot, players respond to Winter with text messages to which the AI responds on the fly. With the goal of achieving a sense of natural conversation with elements of guile, similar to that depicted in the movie “She,” Gadney uses machine learning to create natural saturation and tension. “We wanted to achieve this surprise, which only happens when the car goes beyond common sense and creates a situation that no one expected ,” he says. “As humans, we tend to share information. It makes everything very believable . ”
Software in the traditional sense is a set of strict rules that are respected by the machine to the letter. Typically, a computer only executes a chain of commands, but machine learning allows the computer to identify rules over time and experiment. “Machine learning is defined as a class of programs in which performance improves over time ,” explains Pradeep Dubey, Intel Fellow and Director of Parallel Computing Lab. “The more data the system consumes, the better it gets.”
Machine learning and artificial intelligence technologies open up a world of creative possibilities
George Dolbier, Technical Director of IBM Interactive Media in North America, describes machine learning as “a way to write software not with code, but with data . ” “The program makes its choice, performs actions based on statistics and changes behavior based on new data, ” he says.
Due to its flexibility, machine learning and AI technologies open up a whole world of new creative possibilities, says Dolbier. They can be applied.“In almost all aspects of the gaming experience in the future, for example, in decisions on how to adjust the level of difficulty and the reward system for special players, by analyzing large amounts of player data or in creating completely fictional characters with whom we can interact ,” he says.
In May, for example, SethBling, a YouTube blogger, wrote a program called MarI / O that learned to play Super Mario World (1990) . Unlike other AIs, she started without preliminary instructions, and learned to pass the level like ordinary players: trial and error. MarI / O did not have to “think” how to get through the game. After each death, she repeated successful actions and tried random ways to avoid failure. Despite being close to human abilities, the MarI / O machine way of thinking remained obvious due to her focus on achieving her final goal, ignoring temptations such as bonuses and coins along the way - a human player would most likely not lead yourself in a similar way.
Machine learning may not yet be ready to fully reproduce human behavior, but Gadney believes that it can bring more human into people's interactions with technology. “As we grow, we learn the world through emotions and experience,” he explains. “And if we can use machine learning to reproduce this experience and make it interactive, I think we are doing what we need . ” The uniqueness of The Suspect lies in machine learning, but this does not mean that the game writes itself or that the plot is arbitrary. It has been used in combination with other, more traditional forms of game design.
Gadney says it's best to take it nowmachine learning in game design as another tool, like a brush. This tool is far from perfect. In March, Microsoft's Twitter bot, Tay, was supposed to learn how to conduct informal conversations with those who interact with it. But after 24 hours of directional trolling , she began to hate everyone and cast curses, and was turned off. This case proves the need to strike a balance between freedom and certain rules. Such as taking into account the existence of trolls on the forums.
It is likely that one day machine learning will become as flawless and individual as it was shown in the movie “She . ” Today's games are far from that, but according to the creator of Alien Child, David O'Reilly, a whole new world is opening in front of us, in which players can talk and build more natural relationships with AI. Machines will give odds to human intelligence, says Dubey. “Now this is not just a theory. In practice, cars sometimes show much more accurate results than the best of people . ”
On this happy note, we congratulate everyone on the upcoming New Year, see what new things will bring us in the new year. Well, we hope to please you with interesting translations in the new year. Subscribe to the blog. And also at the beginning of 2017, we can meet with you personally at our open events: the open door day on educational programs of the gaming industry on January 25 and at our conference on creating games on February 11. Admission is free everywhere, only by registration. Do not forget to go through it.
If you have questions, write them in the comments, I will be glad to discuss.