Korben_Dallas
Zwame Advisor
"Every computer game player knows that real life can intrude at the most inopportune moments.
Just when you are completing a tricky flanking manoeuvre, or have got to the darkest point of a dungeon, the phone will ring, a partner will want to talk or your dinner will be on the table.
But Israeli game maker Majorem could have a solution to this problem, at least for players of its forthcoming Ballerium online game.
The company has developed an artificial intelligence system that learns a gamer's style of play and can take over and play for them if they have to spend time away from the game.
Ballerium is an online real-time strategy game in which players create empires by controlling and creating groups of creatures, building cities and castles and gathering money and magical items.
Urgency is lent to their task because the world is gradually decaying and the only way off it is to create a gate that will let a player's followers escape their doom.
The world is populated by a series of bizarre races including the warlike Chiki-Kah, the Olligar, who are artisans, and the scheming Nee.
Adi Gaash, co-founder and chief executive of Majorem, said only by completing a series of quests would players be able to secure all the parts to build the gate.
He said many players of online games become frustrated because their lifestyle limited their interaction with a game world.
But he said the AI system in Ballerium could help players take part even when they were not sat in front of their computer.
"The AI is based on genetic algorithms and can learn a player's style," Mr Gaash told the BBC programme Go Digital.
The AI system looks over the shoulder of a player while they are taking part and learns how they approach battles, whether they expand quickly or are more cautious.
Genetic algorithms work by copying techniques from biology to breed the best solution to a problem.
Typically they involve creating lots of slightly different solutions to a problem, testing to see which perform best and then taking and randomly mutating these to produce a new batch that are again tested, mutated and so on.
Mr Gaash said Majorem was already testing Ballerium with thousands of players and the final game should be released in February 2003."
Fonte: BBC News
Acham este sistema util ou nao confiam na AI do jogo? Eu pessoalmente nao me agrada o facto de andar "outra pessoa" a jogar o meu RPG por mim
Just when you are completing a tricky flanking manoeuvre, or have got to the darkest point of a dungeon, the phone will ring, a partner will want to talk or your dinner will be on the table.
But Israeli game maker Majorem could have a solution to this problem, at least for players of its forthcoming Ballerium online game.
The company has developed an artificial intelligence system that learns a gamer's style of play and can take over and play for them if they have to spend time away from the game.
Ballerium is an online real-time strategy game in which players create empires by controlling and creating groups of creatures, building cities and castles and gathering money and magical items.
Urgency is lent to their task because the world is gradually decaying and the only way off it is to create a gate that will let a player's followers escape their doom.
The world is populated by a series of bizarre races including the warlike Chiki-Kah, the Olligar, who are artisans, and the scheming Nee.
Adi Gaash, co-founder and chief executive of Majorem, said only by completing a series of quests would players be able to secure all the parts to build the gate.
He said many players of online games become frustrated because their lifestyle limited their interaction with a game world.
But he said the AI system in Ballerium could help players take part even when they were not sat in front of their computer.
"The AI is based on genetic algorithms and can learn a player's style," Mr Gaash told the BBC programme Go Digital.
The AI system looks over the shoulder of a player while they are taking part and learns how they approach battles, whether they expand quickly or are more cautious.
Genetic algorithms work by copying techniques from biology to breed the best solution to a problem.
Typically they involve creating lots of slightly different solutions to a problem, testing to see which perform best and then taking and randomly mutating these to produce a new batch that are again tested, mutated and so on.
Mr Gaash said Majorem was already testing Ballerium with thousands of players and the final game should be released in February 2003."
Fonte: BBC News
Acham este sistema util ou nao confiam na AI do jogo? Eu pessoalmente nao me agrada o facto de andar "outra pessoa" a jogar o meu RPG por mim
), ou seja, podemos de um momento para ou outro, numa batalha importante, sacar um truque da manga e conseguir ganhar uma batalha 
