#Angry bots solve generator
A big training problem is that the researchers don't have access to the official level generator and so cannot perform training on extended levels. On a training set consisting of 21 levels the network was able to solve unseen levels showing generalization. The task is particularly interesting because there are many levels and each introduces new features. There have been a number of AIBirds competitions since 2012 and the latest saw the entry of a Deep-Q learning network of the sort used to successfully solve Atari games by DeepMind.
Therefore, to successfully solve the task, a game agent should be able to predict or simulate the outcome of it is own actions a few steps ahead." For example, a poorly chosen first action can make a level unsolvable by blocking a pig with a pile of objects. Secondly, the game requires a planning of sequence of actions, which are related to each other or finding single precise shot. "Firstly, this game has a large number of possibilities of actions and nearly infinite amount of possible levels, which makes it difficult to use simple state space search algorithms for this task. A recent research paper by Ekaterina Nikonova and Jakub Gemrot of Charles University (Czech Republic) suggests the following: You must know the game, but just in case you don't it involves firing the angry birds from a slingshot and hitting various structures - basically it's fun to destroy things. The game, unlike many that AI has proved to be best at, involves a physics simulation courtesy of Box2D. Humans! Rest easy we still beat the evil AI at the all-important Angry Birds game. Recent research by Ekaterina Nikonova and Jakub Gemrot of Charles University (Czech Republic) indicates why this is so.Īngry Bird is a fun and seemingly simple game but it is harder than it looks - for AI at least.
0 kommentar(er)
