Author Topic: epigenetic mutation copy fails after G1 for Shadowgod2  (Read 4355 times)

Offline Shadowgod2

  • Bot Destroyer
  • ***
  • Posts: 387
    • View Profile
epigenetic mutation copy fails after G1 for Shadowgod2
« on: November 28, 2013, 02:22:49 AM »
ok i long handed it and it seems to fix it

Offline Shadowgod2

  • Bot Destroyer
  • ***
  • Posts: 387
    • View Profile
Re: Re: Bot Challenges: A New Direction
« Reply #1 on: November 30, 2013, 01:53:48 AM »
this is the save file for the generational epigenetic mem copying issue

Offline Botsareus

  • Society makes it all backwards - there is a good reason for that
  • Bot God
  • *****
  • Posts: 4483
    • View Profile
epigenetic mutation copy fails after G1 for Shadowgod2
« Reply #2 on: November 30, 2013, 10:17:14 AM »
According to what I have so far, when Shadowgods NNet robot reproduces G2 it fails to copy the 15 extra sysvars trough birthtie.

Shadowgod, are you sure there is a birth tie on G2 ?
« Last Edit: November 30, 2013, 10:27:52 AM by Botsareus »

Offline Shadowgod2

  • Bot Destroyer
  • ***
  • Posts: 387
    • View Profile
Re: epigenetic mutation copy fails after G1 for Shadowgod2
« Reply #3 on: November 30, 2013, 11:28:51 AM »
positive i watched it myself and the bot has no way to create any other tie. the test bot you gave me works fine if you don't have the NNet in the same sim and if you do you have to restart to get it to work with only that bot in the sim

Offline Shadowgod2

  • Bot Destroyer
  • ***
  • Posts: 387
    • View Profile
Re: epigenetic mutation copy fails after G1 for Shadowgod2
« Reply #4 on: November 30, 2013, 11:48:09 AM »
for some reason it can't get passed into gen 1 anymore.

Offline Botsareus

  • Society makes it all backwards - there is a good reason for that
  • Bot God
  • *****
  • Posts: 4483
    • View Profile
Re: epigenetic mutation copy fails after G1 for Shadowgod2
« Reply #5 on: November 30, 2013, 02:00:25 PM »
Quote
for some reason it can't get passed into gen 1 anymore.

So it stopped working completely now? Can I please get the sim file? This will give me something to work with...

Offline Shadowgod2

  • Bot Destroyer
  • ***
  • Posts: 387
    • View Profile
Re: epigenetic mutation copy fails after G1 for Shadowgod2
« Reply #6 on: December 01, 2013, 01:20:53 AM »
yea sure only the first 5 pass down

Offline Shadowgod2

  • Bot Destroyer
  • ***
  • Posts: 387
    • View Profile
Re: epigenetic mutation copy fails after G1 for Shadowgod2
« Reply #7 on: December 01, 2013, 01:45:54 AM »
ok back to gen 2 again i reinstalled db and removed all other db copies.

Offline Botsareus

  • Society makes it all backwards - there is a good reason for that
  • Bot God
  • *****
  • Posts: 4483
    • View Profile
Re: epigenetic mutation copy fails after G1 for Shadowgod2
« Reply #8 on: December 01, 2013, 10:47:39 AM »
ok, taking a look right now...

Offline Botsareus

  • Society makes it all backwards - there is a good reason for that
  • Bot God
  • *****
  • Posts: 4483
    • View Profile
Re: epigenetic mutation copy fails after G1 for Shadowgod2
« Reply #9 on: December 01, 2013, 11:02:08 AM »
Indeed, forced you robot to reproduce at 5K energy, epi-genetic memory was not copied.

Offline Botsareus

  • Society makes it all backwards - there is a good reason for that
  • Bot God
  • *****
  • Posts: 4483
    • View Profile
Re: epigenetic mutation copy fails after G1 for Shadowgod2
« Reply #10 on: December 01, 2013, 11:11:52 AM »
How strange, at times the birth tie does not point back to the parent and at times it does.

Offline Botsareus

  • Society makes it all backwards - there is a good reason for that
  • Bot God
  • *****
  • Posts: 4483
    • View Profile
Re: epigenetic mutation copy fails after G1 for Shadowgod2
« Reply #11 on: December 01, 2013, 12:06:14 PM »
really did not want to do this, seems like I have no choice.

The memory will be stored at birth and exposed if the birth tie exists.

Offline Shadowgod2

  • Bot Destroyer
  • ***
  • Posts: 387
    • View Profile
Re: epigenetic mutation copy fails after G1 for Shadowgod2
« Reply #12 on: December 02, 2013, 11:44:33 PM »
so i went back to the original small NNet and tried to fix it and found the problem and when i ran it it got to gen 2 with random mems 0. usually the last 3 input locs were missing but the rest of it (weightings) were there. very strange :huh: