[Computer-go] Mcts and tactics
patrick.bardou at laposte.net
Tue Dec 19 22:57:00 PST 2017
AGZ paper: greedy player based on policy network (= zero look-ahead) has an estimated ELO of 3000 ~ Fan Hui 2p.
Professional player level with Zero look-ahead. For me, it is the other striking aspect of 'Zero' ! ;-)
IMO, this implies that the NN has indeed captured lots of tactics. Even if tactics may not be as important in go as in chess, it still matters a lot, not just in capturing races. It is often at the foundation of the value of a position (e.g.: life & death status of a group; "value of this position is X because there exist sequences such that this black group can either live or link").
Hard to imagine 2p level without a great deal of tactics, just strong positional judgment. Practicaly, for MCTS guided by policy and value networks, this means the policy networks has to assign good prior to tactical moves.
-------- Message d'origine --------
De : computer-go-request at computer-go.org
Date : 20/12/2017 01:57 (GMT+01:00)
À : computer-go at computer-go.org
Objet : Computer-go Digest, Vol 95, Issue 24
Date: Tue, 19 Dec 2017 16:26:00 -0700
From: Dan <dshawul at gmail.com>
To: computer-go at computer-go.org
Subject: [Computer-go] mcts and tactics
<CAN8pvoThwxz2cSMLkFZJTL_hYvaS6tchzE3YgJQoZV6Vic+u-A at mail.gmail.com>
Content-Type: text/plain; charset="utf-8"
It is known that MCTS's week point is tactics. How is AlphaZero able to
resolve Go tactics such as ladders efficiently? If I recall correctly many
people were asking the same question during the Lee Sedo match -- and it
seemed it didn't have any problem with ladders and such.
In chess and shogi, there is lots of tactics and plain MCTS as used in
AlphaZero shouldn't perform well (one would expect), but apparently
AlphaZero didn't seem to have a problem in that regard against stockfish.
First of all, I think that AlphaZero is resolving tactics by growing its
MCTS tree very rapidly (expand after each visit) -- some people thought
initially that NN may have some tactics in it but I don't believe it can do
better than a quiescence_search. Tactics requires precise calculations with
moves that maynot make sense (sacrfice) -- apparently AlphaZero's
positional understanding led it to be superior in this regard as well.
My simple MCTS chess engine (single thread) is now better in tactics than
it used to be (after removing the rollouts), but it is still far far from
the tactical ability of alpha-beta engines with LMR+nullmove. What do you
think is AlphaZero's tactical strength coming from ? I am guessing parallel
MCTS with larger exploration coefficient for each thread -- this should
explore enough not so good moves closer to the root not to miss sshallow
I just wanted to know the opinions of the MCTS experts.
-------------- next part --------------
An HTML attachment was scrubbed...
More information about the Computer-go