Neural AI

23.02.2017

Greetings, commanders!

Nival is reporting that we've been working on solving one of the most ambitious problems for artificial intelligence specialists. Company’s engineers created the world’s first neural network AI for the real-time strategy. This challenging task was chased by a large number of leading companies, including the Deep Mind, IBM, etc. AI, named Boris, is capable of playing at the top player’s level while not using any hidden information about the enemy.

Every few seconds AI, who we kindly named general Boris, analyzes the gaming session and makes neural network-based predictions of the enemy future behavior. This approach allows him to think up sophisticated counter-strategies and bring them to life.


The video of AI ​​playing against one of the studio staff was published on the the official Blitzkrieg 3 channel on YouTube and on the game's page on Steam. It stresses the AI’s unusual behavior: Boris constantly scouts the map, actively relocates his units, and changes his tactics depending on the situation. For instance, in one of the episodes Boris started by landing his paratroopers to attack a single enemy tank. But when reinforcements tanks came, his troops immediately took the defensive positions in the buildings and tried to utilize the artillery.

The video also states that playing with general Boris will be available for general public at the upcoming March update.

"Despite the fact that the leading companies of the world are working on this problem, we have managed to create the first neural network AI for RTS", - says Sergey Orlovskiy, founder and CEO of Nival. "It is worth noting that Boris plays fairly. He does not use the information under the fog of war, as well as any other hidden information about the enemy. We gave him only the basic tactical moves, but during his training he invented a variety of strategies. He makes decisions just like a talented military leader. It has become difficult to predict his actions now, and, most importantly, to distinguish them from human behavior."

We also state that such an AI approximates the not-so-distant future. Sooner or later AI-based generals will surpass their human counterparts and AI-controlled armies will defend the national borders.