I am talking about relationships between AIs (e.g. 2 of them forming a couple, 3+ in family like relationship).
What knowledge could come out of such experimentation?
$\begingroup$
$\endgroup$
6
-
2$\begingroup$ Does swarm robotics fit your question? $\endgroup$– Basile StarynkevitchNov 2, 2016 at 18:58
-
$\begingroup$ If there is a single/common goal, how do define the boundaries between the AIs if they are integrated in one system? If there are separate goals for each of the AIs then what is the interaction for? $\endgroup$– Iliyan BobevNov 2, 2016 at 19:27
-
2$\begingroup$ en.wikipedia.org/wiki/Generative_adversarial_networks $\endgroup$– BlindKungFuMasterNov 3, 2016 at 9:04
-
$\begingroup$ @Basile Starynkevitch: Yes definitely! I would like to get an input on that as well. I actually did not think of it at first. $\endgroup$– K_RolNov 3, 2016 at 14:38
-
$\begingroup$ For physical example, see: How can thousand-robot swarm coordinate their moves without bumping into each other? $\endgroup$– kenorbNov 4, 2016 at 11:19
|
Show 1 more comment
1 Answer
$\begingroup$
$\endgroup$
One example might be self-play in games. Since neural networks and deep learning depend on massive amounts of data, one way to generate data is to have two virtual machines play each other and record the experience. An example discussion can be found at http://www.cs.cornell.edu/boom/2001sp/Tsinteris/gammon.htm which uses reinforcement learning. I believe AlphaGo also uses this technique of self-play, and uses two independent neural networks, one reducing the search space and the other deciding on the best move in the remaining space, that in a sense cooperate to decide on the next move.
