[ad_1]
Photo: Referential
(Caracas, July 05, News24) .- In recent months there have been great advances in the field of Artificial Intelligence (AI) but sometimes engineers you can afford to teach trivial things to these platforms; How to play Atari
This happened with the friends of OpenAI, who presented the results of their most recent project on the field, they taught an AI to play the classic Atari, Montezuma & Revenge
. To succeed in a reinforced learning project, an AI must do two things:
First, find a sequence of actions that leads to a positive reward, that is the problem of l & # 39; exploration.
Then, remember the sequence of actions to take and generalize it to related situations; but slightly different, this is the problem of learning
They were the basic points of the OpenAI project, where the best way to find their goal was to achieve video recordings.
Different members of the video team were recorded playing sessions a little over ten minutes of the game, so Artificial Intelligence analyzed the games and learned what to move forward in each scenario. Thus, the human demonstration of the game allowed to obtain 71 500 points at the end of its session. Artificial intelligence has imitated the road; but he made 74,500 points.
Source: Informe21
Post Views:
118
[ad_2]
Source link
