Hacker News Reader

Comment by drcode | Hacker News Reader

I think this is somewhat incorrect- The creators of AlphaGo made it clear that their system does not take the opponent into account at all, it just answers the question "What is the strongest move right now?" and plays that move, without taking the opponent into account. In other words, it does not have any mental model of the opponent.

However, you are correct insofar that it doesn't care about winning by large margins, it prefers winning by smaller margins if it can achieve this with a higher win probability.

View on HN

A perhaps more accurate way to say it is that AlphaGo's models its opponents as a copy of itself.

So do human players, with rare exceptional ocassions

Playing trap moves is not that rare and it shows that you expect the opponent not to know a complicated variation.

Strong players dont play "trap moves"

Who said anything about strong players?

> AlphaGo

human players are not alphago

The context of this thread is AlphaGo. Why would we bother discussing what bad human players do when the topic is clearly about play at the highest levels?

The highest level players play special variations against each other hoping that the other player doesn't know it. They CLEARLY play against what they think the other player knows, not what they know (since they have studied this variation on purpose to prepare)

As a semi-pro player I can assure you thats not how you play Go.

Interesting. From chess it seems that, for important matches, players will deeply study each other's games and try to get the other player into positions that they may be less used to playing and less comfortable with.

Is this not done in go?

Its more important to smoothen out your own weaknesses than looking for your opponents. A weakness in your style of play is going to make you lose way more many games than your ability to find some weaknesses in some other player.

To become a pro you have to go through insane levels of competitions, you need to be strong, not find a weakness in the 100's of players you will face to just have a shot to become the lowest level of professional.

That's just appeal to authority. Lee Sedol's move against AlphaGo in game 4 could be considered a trap because it actually didn't work, but it was complicated enough to trick AlphaGo.

Appeal to authority is only deductively invalid, not inductively invalid.

But it's not even a good authority, since strong amateurs (semi-pros) have many opponents (amateur tournaments are played in the same day or weekend and have many matches), while top players prepare specifically for one opponent in tournament finals (each match played on a different day).

You never study your up coming opponents previous games?

As a pro you study everyones games as a mean to get all the latest information possible, but there isn't really much you can do as a top pro to play against your opponents likings: the era were that could bear fruits ended decades ago.

For example, US Congress has a lot of matches in a day so you don't even know who you're going to face. Only top players study the games of their opponents because they have time to prepare in finals of big tournaments.

All competitive-game-playing AIs ask, "What will my opponent play in response to this move?" It's possible for an AI to evaluate a move based solely on the resulting board position, but it wouldn't be very good. Pretty much all AIs play many turns out to see if the move is any good. In the case of AlphaGo and Monte Carlo tree search, they actually play to the end of the game many times. To do this, they must of course play moves for each player.

Ah but I think the key here is that it doesn't say "how will this player respond" but "how would a player respond".

No matter how I've played against it to get to where we are, it'll play the same from that point on. It won't identify me as a risky player from my pattern, nor will it try and classify me as "unpredictable" in some way. It'll play each move as though it has sat down at an already in-progress game between two random opponents.

> It's possible for an AI to evaluate a move based solely on the resulting board position, but it wouldn't be very good. Pretty much all AIs play many turns out to see if the move is any good.

I would strongly argue that these are identical situations. Playing out scenarios in your head but taking into account no history is the same as "evaluating a move based solely on the board position".

Reply on news.ycombinator.com