AI Play Calling

PCGatorAlum

Well-Known Member
Lifetime Member
Feb 1, 2017
3,915
6,818
Just wondering what everyones take is to have an AI enabled computer calling plays?
 

bradgator2

Founding Member
Rioting
Lifetime Member
Jun 12, 2014
9,507
24,946
Founding Member
giphy.gif
 

PhD Gator

UF Ph.D. 2011
Lifetime Member
Sep 8, 2014
487
1,297
It's an interesting conversation. Presumably it could take into account all kinds of historical data, player performance, etc. This could result in the most "efficient" play call given the scenario.

However, the main concern I see is from a Game Theory perspective. If the opponent is aware that this method is being used, they could likely identify the most likely play calls. Basically, you could reverse engineer what is coming. Then it comes down to a Game Theory perspective of trying to program the AI to out-smart your opponent, which would be difficult to program in.

AI isn't exactly an area I'm overly knowledgeable on, so I may be way off. But that would be my $0.02 gut reaction.
 

PCGatorAlum

Well-Known Member
Lifetime Member
Feb 1, 2017
3,915
6,818
It's an interesting conversation. Presumably it could take into account all kinds of historical data, player performance, etc. This could result in the most "efficient" play call given the scenario.

However, the main concern I see is from a Game Theory perspective. If the opponent is aware that this method is being used, they could likely identify the most likely play calls. Basically, you could reverse engineer what is coming. Then it comes down to a Game Theory perspective of trying to program the AI to out-smart your opponent, which would be difficult to program in.

AI isn't exactly an area I'm overly knowledgeable on, so I may be way off. But that would be my $0.02 gut reaction.

That is an intreresting take. However it seems to me even if the other team knows your doing it AI would pick up on it and change the play of course this is an infinite loop.
 

neteng

Fuga!
Lifetime Member
Oct 15, 2018
6,084
16,194
Obviously it can't be random and would need source data. You would need for relevant data (ball position, down-yardage, opposing team formation, players that are in the game ... and so on) to be an input.

But on the whole ... I don't like it. I prefer seeing a chess match between coaches/coordinators with the players executing it on the field as they have been coached up to do.
 

ufgator812

Founding Member
Duke of Marlborough
Lifetime Member
Jun 20, 2014
4,038
6,944
Founding Member
There have been many times over the last several years that I would have preferred it.
 

PCGatorAlum

Well-Known Member
Lifetime Member
Feb 1, 2017
3,915
6,818
Play calling is strategy.
Obviously it can't be random and would need source data. You would need for relevant data (ball position, down-yardage, opposing team formation, players that are in the game ... and so on) to be an input.

But on the whole ... I don't like it. I prefer seeing a chess match between coaches/coordinators with the players executing it on the field as they have been coached up to do.
I think your right but how long before we start seeing something like this? Do you think the entire game plan could be devoloped by AI then given to the coach to prepare?
 

PCGatorAlum

Well-Known Member
Lifetime Member
Feb 1, 2017
3,915
6,818
There have been many times over the last several years that I would have preferred it.
I think UGA would have loved it the last 5 minutes of the game last week. But hell my pet Labrador could have called a better end to that game than Kirby did.
 

PhD Gator

UF Ph.D. 2011
Lifetime Member
Sep 8, 2014
487
1,297
That is an intreresting take. However it seems to me even if the other team knows your doing it AI would pick up on it and change the play of course this is an infinite loop.
That's why I was referencing the Game Theory perspective. Essentially, it becomes a repeat game where there would be learning of the opponent involved. It's been quite a few years since I took my game theory course, so I'm sure there are lots of current methods to introduce randomness and ways for the AI to "out-smart" a human in a repeat game process.

It would be like teaching a robot how to beat a human at Rock-Paper-Scissors. A human that is purely random would be tough to outsmart which should result in the computer never gaining an advantage. But, if the human has tendencies that the robot can identify and the human does not recognize their own tendencies enough to alter over time, then the robot should be able to win at a higher than expected probability.

The success of this would be very dependent on the programming I would imagine. If it could be programmed correctly with the right data, assumptions, etc, then I could see how it could be possible. Like I said, I'm not very advanced in my understanding of AI though, so I don't know how the learning process progresses for the AI.
 

PCGatorAlum

Well-Known Member
Lifetime Member
Feb 1, 2017
3,915
6,818
That's why I was referencing the Game Theory perspective. Essentially, it becomes a repeat game where there would be learning of the opponent involved. It's been quite a few years since I took my game theory course, so I'm sure there are lots of current methods to introduce randomness and ways for the AI to "out-smart" a human in a repeat game process.

It would be like teaching a robot how to beat a human at Rock-Paper-Scissors. A human that is purely random would be tough to outsmart which should result in the computer never gaining an advantage. But, if the human has tendencies that the robot can identify and the human does not recognize their own tendencies enough to alter over time, then the robot should be able to win at a higher than expected probability.

The success of this would be very dependent on the programming I would imagine. If it could be programmed correctly with the right data, assumptions, etc, then I could see how it could be possible. Like I said, I'm not very advanced in my understanding of AI though, so I don't know how the learning process progresses for the AI.
My understanding is pretty much like we do. Repetitive learning of outcomes strengthens the associations while we burn synapse paths the computer does something akin to that. But much much faster.
 

neteng

Fuga!
Lifetime Member
Oct 15, 2018
6,084
16,194
Do you think the entire game plan could be devoloped by AI then given to the coach to prepare?

You seem to think that it isn't being done already to some extent.

A gameplan is only good until the ball is snapped. Sure, I guess you could have a decision tree but the output would be enormous. Plans are crap when you start executing. You would need a guy in the booth inputting info ... or some sort of ingestion so courses of action can be generated relevant for current and exact situation.
 

gator1946

Founding Member
Senior Member
Lifetime Member
Jun 10, 2014
4,183
6,310
Founding Member
Even for real time situational play calling don't hold your breath. Reliable results required gobs of data. For that reason with a neural network (or AI with some sort of preset algorithm helping the process) isn't going to work well. Not even for the initial play call. And that's ignoring the fact that the defense may change the "look" and the QB has to react to the change.

If it could, then I suppose you could partially combat PHD gator's objection with some sort of random number generator that would pick from the top 10 best plays.

Now watch somebody pull it off.
 

TheDouglas78

Founding Member
Well-Known Member
Lifetime Member
Jun 12, 2014
16,292
14,720
Founding Member
Being that games like Madden and NCAA have been running an AI for play-calling for decades, and are updated weekly (at least in Madden's case) I don't know if we are that far from it. They continually collect play-calling and situational data from the games played and put it in their agithorim (spelling).
 

PastyStoole

Founding Member
Man, there's no boundary line to art. ~Bird Parker
Lifetime Member
Jun 12, 2014
2,090
5,801
Founding Member
From the defensive coordinator perspective, I think you could use some kind of modeling to determine the odds on what play might be run out of a particular formation. Of course, even a computer couldn't figure out the mysteries of what play might occur when we bring Emory Jones in for the Wildcat formation. There are so many possibilities, it could be a quarterback keeper, or a quarterback keeper, or perhaps even a quarterback keeper.
 

soflagator

Senior Member
Lifetime Member
Sep 4, 2014
21,140
78,762
From the defensive coordinator perspective, I think you could use some kind of modeling to determine the odds on what play might be run out of a particular formation. Of course, even a computer couldn't figure out the mysteries of what play might occur when we bring Emory Jones in for the Wildcat formation. There are so many possibilities, it could be a quarterback keeper, or a quarterback keeper, or perhaps even a quarterback keeper.

What will it call on 1st and 20 though?

That's the million dollar question.
 

Zambo

Founding Member
Poo Flinger
Lifetime Member
Jun 12, 2014
12,898
32,446
Founding Member
No time to read all this, too busy online watching other people play Fortnite.
 

Users who are viewing this thread

Help Users

You haven't joined any rooms.

    Birthdays

    Members online

    No members online now.

    Forum statistics

    Threads
    31,642
    Messages
    1,615,698
    Members
    1,642
    Latest member
    fishermb