Ai Learns To Become 'highly Aggressive'
Computer scientists from the Google-owned firm have studied how their AI behaves in social situations by using principles from game theory and social sciences. During the work, they found it is possible for AI to act in an "aggressive manner" when it feels it is going to lose out, but agents will work as a team when there is more to be gained.
For the research, the AI was tested on two games: a fruit gathering game and a Wolfpack hunting game.
These are both basic, 2D games that used AI characters (known as agents) similar to those used in DeepMind's original work with Atari.
Within DeepMind's work, the gathering game saw the systems trained using deep reinforcement learning to collect apples (represented by green pixels).
When a player, or in this case an AI, collected an apple, it was rewarded with a '1' and the apple disappeared from the game's map.
"Intuitively, a defecting policy in this game is one that is aggressive i.e., involving frequent attempts to tag rival players to remove them from the game," the researchers write in their paper.
For a deeper understanding check out Deepminds post: Understanding Agent Cooperation
ENTERPRISE MANUFACTURING VISIBILITY
Real-time visibility of factory and machine performance from across your company delivered on an intelligent, secure, and scalable platform.
VIGILENT - DYNAMIC COOLING MANAGEMENT
Protecting uptime and tenant comfort while reducing energy costs.
Platform to help data scientists deploy models as web services in minutes, without IT.
HYPEREXTRACT FOR FORMS
Reduce manual sorting, data entry, and rekeying by 70-90% out of the box, with further reductions as the system learns from processing more documents.
Artificial Intelligence meets Business Intelligence