I´m currently implementing NEAT. What should I do when in a mutation the same Innovation occurs which has already happened to that genome?
Should I simply ignore it?
If not what do I do with it in the mating part?
2
$\begingroup$
$\endgroup$
-
1$\begingroup$ What do you mean exactly? The NEAT algorithm doesn't make it possible that the same innovation occurs twice in the same genome. $\endgroup$ – Thomas W May 6 '17 at 14:27
-
$\begingroup$ @ThomasW where exactly does he says this. I can´t remember reading this. $\endgroup$ – Miemels May 6 '17 at 14:29
3
$\begingroup$
$\endgroup$
Because this is more of an answer than a comment:
In the add connection mutation, a single new connection gene with a random weight is added connecting two previously unconnected nodes.
So two nodes that have been mutated with a connection, can't remutate because the nodes should be unconnected.
In the add node mutation, an existing connection is split and the new node placed where the old connection used to be. The old connection is disabled and two new connections are added to the genome.
The old connection is disabled, so the same mutation can't occur again on this connection. In practice, you can just remove the disabled connection, because it will be formed again with the add connection mutation.
-
$\begingroup$ Okay. I must have over read the previously unconnected part. Thanks $\endgroup$ – Miemels May 6 '17 at 14:42
