[halfnhalf]

Don't table tennis players learn to predict how the ball will act based on their opponents movements? Seems like if they aren't able to do that with a robot opponent (who doesn't look or behave like a human) then they wouldn't be able to play at their best.

[LeCompteSftware]

Yes, you're dead on:

  Rui Takenaka, an elite-level player who has won and lost matches against Ace, said in comments provided by Sony AI: "When it came to my serve, if I used a serve with complex spin, Ace also returned the ball with complex spin, which made it difficult for me. But when I used a simple serve - what we call a knuckle serve - Ace returned a simpler ball. That made it easier for me to attack on the third shot, and I think that was the key reason why I was able to win."

It seems like the human players might be playing in a way that tacitly overestimates their AI opponents' intelligence and underestimates their skill. AFAIK the SOTA Go AIs are still vulnerable to certain very stupid adversarial strategies that wouldn't fool an amateur (albeit they're not something you'd come up with in normal play, more like a weird cheat code). I wonder if this could get ironed out with a bit more training against humans vs. simulation.

[ACCount37]

I do expect this to have a "novelty edge" over human opponents - which can be closed with practice, on the human end.

And, like many AIs, it can have "jagged capability" gaps, with inhuman failure modes living in them - which humans can learn to exploit, but the robot wouldn't adapt to their exploitation because it doesn't learn continuously. Happened with various types of ML AIs designed to fight humans.

[Ferret7446]

Only if you assume the AI can't improve. Otherwise, AI has a fundamental edge over humans in that they don't get old and die, and can be copied perfectly without an expensive retraining period

[ACCount37]

Oh, they can. They just need a human touch to actually improve.

For now. It's a work in progress.

[zingar]

Chess players learned to exploit chess computers’ weaknesses in the beginning too, but they can’t any longer. This version of the robot might not learn continuously, but the next will be better.

[cool_dude85]

I believe there are still some echoes of the concept. Even top engines will play certain grandmaster draw lines unless told more or less explicitly not to. So if you were playing a match against Stockfish you'd want to play the Berlin draw as White every time, for example.

[NickC25]

But chess is a turn-based game where there's no deception (in the sense that both players can see all legal moves for both themselves and their opposition at all times), whereas in table tennis, it's in real time, it's fast as hell, the table is small, and the ball can have 2 or 3 different spin types from the same arm/hand/wrist movement , and can land in a number of different spots.

[philwelch]

Interesting point. There are a lot of sports (football, basketball) where the cumulative rules end up requiring any player to have a humanoid form (references to elbows and knees and hands and feet, etc.), but even in ping pong it kind of seems like cheating to have a non-humanoid form factor.

[dethos]

Exactly. There are cues that an opponent provides when approaching a ball that help the player prepare for and limit the range of possible responses (this happens with most racket games). With these robots, the players only find out after the ball is already coming in their direction.

I wonder how much practice these players had against the machine in the weeks leading up to the actual game. That would be significant to ensure they are playing at their pro level.

[hermitcrab]

You can predict the movement of the ball (speed, direction, spin) based on the movement of the bat relative to the ball. What the rest of the player's body is doing is irrelevant to predicting what the ball will do - but relevant to predicting where they will be when you make the return shot.

[perlgeek]

That's not how humans operate though.

Humans use every clue they can get to predict the trajectory as early as possible. For example most players use a roughly similar technique for a certain stroke, e.g. the forehand topspin. They also tend to have a pretty narrow angle that they usually play it, relative to their body and their movement. Players use that predict where the ball will move, and position themselves accordingly. And they start that movement before their opponent has touched the ball.

Some players can deceive others by bending their wrist right before ball contact, which sends the ball in an unexpected direction (but that usually comes at the cost of an increased risk of missing the shot).

Similarly, the size of the stroke limits the pace (and spin) you can apply to the ball; when the opponent starts a short stroke, you can be sure the shot won't be fastest, and move closer to the table.

[hermitcrab]

What the ball does is only determined by the contact with the bat. But it is true that you can often correctly predict what the bat will do based on the movement of the player's body.

[dethos]

The movement of the "bat" is tied to the physical limitations of the arm and the positioning of the body. Something that can't be deduced or even perceived clearly from the movements of this robot.

As I mentioned in a previous comment, it would be important to know how many weeks of preparation and training against this sort of robot the player had before the match.