SUBSIM Radio Room Forums



SUBSIM: The Web's #1 resource for all submarine & naval simulations since 1997

Go Back   SUBSIM Radio Room Forums > Modern-Era Subsims > Dangerous Waters > DARPA Game – “ACTUV Tactics”
Forget password? Reset here

 
 
Thread Tools Display Modes
Prev Previous Post   Next Post Next
Old 04-08-11, 01:56 AM   #11
Enigma738
Bilge Rat
 
Join Date: Apr 2011
Location: Canada
Posts: 1
Downloads: 0
Uploads: 0
Default

Hey guys, I finally came out of lurking on these boards to add my thoughts to the discussions.

So far I've just had a few runs with it tonight and have the game play down pat. Apart from my very first run, I've been in the Triton all this time, so I don't have much to add to the Shark discussion so far.

What I *can* bring to the table is a neat and relevant topic from the realms of artificial intelligence. No matter how 'smart' an AI agent may appear, it's often just doing the same thing we're doing - searching for the minimums and maximums for a problem. Understandably, a computer is much better suited for the raw calculations, hence why we trust in Excel to plot out our functions when we want to make sense of things.

The flip side to this is that we possess a HUGE advantage over a given computer in that we've been around for far longer and have thus gathered much more experience in life. All those hours of playing catch, watching traffic to know when it's safe to cross, those are all examples of us using the basic object tracking skills we have. We're way better than we give ourselves credit for!

... In fact, we're so good at making very quick and rational decisions with such reliability that it's common to collect data from human trials in complex scenarios to save the young and fresh AI agent from having to learn on its own. Collectively, we're striving for the top scores and figuring out tactics, consider it being a parent to the brains that will make ACTUV run. Without the help gathered from this software, it'd take a lot of resources to essentially re-invent the wheel.

After collecting enough data from us the computer can start to make use of its talent with numbers to smooth out our human mistakes, like hitting the wrong key, or selecting the best strategies to work with for each small part of the problem. Stitch those together and you have yourself a fairly well suited brain for tactical tracking!

Pretty neat stuff, I have to say, hope it's an enjoyable read!
Enigma738 is offline   Reply With Quote
 


Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off

Forum Jump


All times are GMT -5. The time now is 06:42 AM.


Powered by vBulletin® Version 3.8.11
Copyright ©2000 - 2024, Jelsoft Enterprises Ltd.
Copyright © 1995- 2024 Subsim®
"Subsim" is a registered trademark, all rights reserved.