Contact us

Could you train your vacuum cleaner like your dog?

Author: Tomasz Tajmajer

Artificial intelligence methods are often perceived as extremely complicated and understandable only by people that graduated computer science. The idea of an electronic device that, by tself, learns how to behave still seems to be very futuristic. In fact, we have many “smart” devices around us, but many of them are not smarter than a motion-based light switch. Yet, our world is full of intelligent agents: rats, cats, dogs, cockroaches and humans. The secret behind their behaviors lies in millions of years of evolution and something that we all know: trials and errors, rewards and punishments. 

Let’s imagine a rat in a specially designed rat cage that has a button and a food supplier. When the button is pressed, a portion of food is supplied. A rat placed in such cage for the first time will use its senses to more or less randomly explore his new environment. At some point, the rat will press the button and receive a reward – some food will be supplied. Over time this situation will repeat and finally, the rat will learn that pressing the button releases the food. From now on, the rat will exploit his knowledge each time he feels hunger. 

Now, consider a robotic vacuum cleaner – like one of those currently available on the market. Such a vacuum cleaner is able to autonomously move around the room and clean the carpet or the floor. It is smart enough to avoid collisions with various objects, it may also automatically return for recharging or be used by a cat as a taxi. Let us however assume that the vacuum cleaner comes with no predefined “intelligent” behavior at all – it just moves randomly hitting everything around. Would it be possible for the vacuum cleaner to learn by itself how to behave? Could it correct its behavior just by knowing that it done something wrong? In fact it could – using reinforcement learning.

Read whole article – train_a_vacuum_cleaner_like_your_dog

You might also like

AAIA’17 Data Mining Challenge Concluded

AAIA’17 Data Mining Challenge is the fourth data mining competition organized within the framework of International Symposium Advances in Artificial Intelligence and Applications. This time, the task is to come up with an efficient prediction model which would help AI to play the game of Hearthstone: Heroes of Warcraft. The competition is kindly sponsored by Silver Bullet Solutions and Polish Information Processing Society (PTI).

Read more
Next challenge for AI after winning with top human chess, go and poker players

In chess and go games all information needed for AI analysis is literally on the table. According to game experts winning in no-limit poker shows that AI is ready to win in cybersecurity, negotiations, military, auctions and even in containing infections.

Read more
Praga 2017

AAIA’17 Data Mining Challenge: Helping AI to Play Hearthstone took place between March 23 and May 15, 2017. It was organized under the auspices of the 12th International Symposium on Advances in Artificial Intelligence and Applications and sponsored by Silver Bullet Solutions and Polish Information Processing Society.

Read more
Lecture on Artificial Intelligence in Games

29.12.2016 Leon Koźminski Academy of Entrepreneurship and Management, Warsaw, Poland

A lecture given by dr. Maciej Świechowski and dr. Piotr Beling

The goal of the lecture was to present an overview of modern approach to artificial intelligence in games.  The lecture was organized in two parts. First was devoted to application of Artificial Neural Networks (ANN) to different aspects of Machine Learning in general and to computer games in particular. The second part was devoted to Monte Carlo Tree Search (MCTS), a technique which might be applied to find optimal decisions in games with perfect or imperfect information.

Read more