Artificial intelligence, deep learning, and skill development

I have compared parents and coaches attempting to control the every movement of their children on a basketball court or soccer field to fantasy football. On Twitter, Innovate FC gave this type of behavior a more eloquent name: Playstation coaching. An article about robots and artificial intelligence provided another metaphor.

“Most robotic applications are in controlled environments, where objects are in predictable positions,” says UC Berkeley faculty member Trevor Darrell, who is leading the project with Abbeel. “The challenge of putting robots into real-life settings, like homes or offices, is that those environments are constantly changing. The robot must be able to perceive and adapt to its surroundings.”

This parallels the current discussion about constraints-led coaching. Most practice drills are in controlled environments, where objects are in predictable positions. The challenge of putting players into real game settings is that those environments are constantly changing. The player must be able to perceive and adapt to its surroundings.

Conventional, but impractical, approaches to helping a robot make its way through a 3D world include pre-programming it to handle the vast range of possible scenarios or creating simulated environments within which the robot operates.

What are plays if not a conventional, but impractical approach to helping players make their way through a game environment? Again, it is not that plays are wrong, but the attitude of “run the play” even when not running the play or deviating from the play leads to a better alternative.

Instead, the researchers turned to a new branch of AI known as deep learning. This is loosely inspired by the neural circuitry of the human brain when it perceives and interacts with the world.

“For all our versatility, humans are not born with a repertoire of behaviours that can be deployed like a Swiss army knife, and we do not need to be programmed,” explains postdoctoral researcher Sergey Levine, a member of the research team. “Instead, we learn new skills over the course of our life from experience and from other humans. This learning process is so deeply rooted in our nervous system, that we cannot even communicate to another person precisely how the resulting skill should be executed. We can at best hope to offer pointers and guidance as they learn it on their own.”

We learn through experience and other humans, but this learning is not like programming a computer, or robot, because we have to adapt our experience or someone’s instructions to constantly changing environments. When we learn to do math, we do not practice every possible math problem; instead, we learn the basics, and we learn to solve problems that are changing constantly.

In basketball, we cannot program every response on the court. Instead, we have to learn to solve problems. Therefore, practice should expose players to problem solving in order to develop this skill, rather than trying to pre-program every potential response to every potential scenario. Playstation coaches attempt to imagine every scenario and teach a play (response) to each scenario. Therefore, they have man offenses, underneath OB plays, sideline OB plays, zone offense vs a 2-3, zone offense vs a 3-2, zone offense vs a 1-3-1, press breaks vs man, 1-2-1-1, 2-2-1, 2-1-2, 2-1-1-1, etc. They spend every moment pre-programming these responses, but in a game, when something is slightly different than expected, the players do not know what to do. They cannot adapt because they have never solved problems on their own; they have never really learned. They have been programmed.

By Brian McCormick, PhD
Director of Coaching, Playmakers Basketball Development League
Author, The 21st Century Basketball Practice and Fake Fundamentals

Tags: , , , , , ,

5 Responses to “Artificial intelligence, deep learning, and skill development”

  1. Paul Cortes says:

    The issue of programming is one that is addressed in the textbook Dynamic Systems: A Constraints Approach. Our understanding of how the brain works has evolved over the years. A century ago, we believed that the brain worked liked a computer program, in which each part (skill) needed to be “programmed” in isolation, in which our simply putting the pieces together resulted in expert performance. Since then, it has been discovered that the brain doesn’t work that way at all, that it is a dynamic system that self-organizes in response to the environment around it. Multiple parts work together at once to form a skill. So instead of breaking things down into parts and putting them back together again, the right approach is to keep everything together and then shape it to the desired response.

    “You must be shapeless, formless, like water. When you pour water in a cup, it becomes the cup. When you pour water in a bottle, it becomes the bottle. When you pour water in a teapot, it becomes the teapot. Water can drip and it can crash. Become like water my friend.”
    ― Bruce Lee

  2. BrianMcCormick says:

    Wow. Dynamic systems and Bruce Lee in one, short comment! Impressive. How do you like that book? It’s one of three that I am considering for the graduate course in Sports Pedagogy and Motor Learning that I am teaching in 2016. As a coach, how practical did you feel that it was?

  3. Paul Cortes says:

    I probably didn’t understand 80% of what was in the book, but I trekked my way through it. I probably need to reread it, as truth be told I don’t remember most of it. But the point I wrote above stuck in my head, as well as the idea of using constraints in practice. All that can be gleaned from more digestible reading, such as this blog, but reading the book solidified those concepts in my mind.

  4. Mike says:

    The concept in that book reminded me of a tweet Brian posted awhile back about “Complexity translating to simplicity easier than the other way around.”
    The longer I teach the more I find myself introducing the concept in its entirety and then starting with the most complex thing I think students can handle and working backwards as far as necessary for those who need it rather tHan with the most simple thing..

    I think people have misunderstood the concept of cognitive chunking. Rather than breaking a process down to as many small pieces as possible we actually break things down into as large and complex pieces as possible. Imagine a child learning to play baseball. They often start with just someone tossing them a ball to hit or catch, not because that is the most simple thing there is but because that is the most complex thing they are ready for. Later they will add extra players and baserunning, etc

    Dean Smith wrote in his book about using the whole-part-whole method. While not the exact same thing, it has similarities. I think this is the beauty of SSG’s, it modifies the complex on a smaller scale but leaves the concept intact to be absorbed.

  5. BrianMcCormick says:

    Mike:
    Good points. In simplest terms, when you practice a technical skill in isolation, you improve only the technical skill; when you practice tactical and technical skills simultaneously, you improve tactical and technical skills. For instance, a 2v0 pick-and-roll drill is really just a shooting/passing/finishing drill, depending on the coach’s instructions. The simplicity does not translate to the more complex pick-and-roll in a 5v5 game. However, if you practice pick-and-rolls in a 2v2 or 3v3 situation, not only do you improve the anticipation and decision-making of the pick-and-roll, but you improve the passing/shooting/finishing. The complexity translates to the simple.

Leave a Reply