Re: [Computer-go] Is MCTS needed?

>On 17-11-17 02:15, Hideki Kato wrote: >> Stephan K:

Re: [Computer-go] Is MCTS needed?

On 16-11-17 18:24, Stephan K wrote: > 2017-11-16 17:37 UTC+01:00, Gian-Carlo Pascutto : >> Third, evaluating with a different rotation effectively forms an >> ensemble that improves the estimate. > > Could you expand on that? I understand rotating the board has an > impact for a

Re: [Computer-go] Is MCTS needed?

On 17-11-17 02:15, Hideki Kato wrote: > Stephan K: >

Re: [Computer-go] Is MCTS needed?

Stephan K:

Re: [Computer-go] Is MCTS needed?

Hideki, This is a very nice observation. s. On Nov 16, 2017 12:37 PM, "Hideki Kato" wrote: Hi, I strongly believe adding rollout makes Zero stronger. They removed rollout just to say "no human knowledge". #Though the number of past moves (16) has been tuned by human

Re: [Computer-go] Is MCTS needed?

While MCTS works "better" in games with a forward direction, it eventually converges to the same answer as alpha-beta in any game. The general architecture is to set a maximum depth, and use a suitable evaluator at the leaf nodes. I haven't done detailed studies, but there is definitely a

Re: [Computer-go] Is MCTS needed?

While MCTS works "better" in games with a forward direction, it eventually converges to the same answer as alpha-beta in any game. The general architecture is to set a maximum depth, and use a suitable evaluator at the leaf nodes. I haven't done detailed studies, but there is definitely a

Re: [Computer-go] Is MCTS needed?

On 16-11-17 18:15, "Ingo Althöfer" wrote: > Something like MCTS would not work in chess, because in > contrast to Go (and Hex and Amazons and ...) Chess is > not a "game with forward direction". Ingo, I think the reason Petr brought the whole thing up is that AlphaGo Zero uses "MCTS" but it does

Re: [Computer-go] Is MCTS needed?

State of the art in computer chess is alpha-beta search, but note that the search is very selective because of "late move reductions." A late move reduction is to reduce depth for moves after the first move generated in a node. For example, a simple implementation would be "search the first

Re: [Computer-go] Is MCTS needed?

Hi, I strongly believe adding rollout makes Zero stronger. They removed rollout just to say "no human knowledge". #Though the number of past moves (16) has been tuned by human :). Hideki Petr Baudis: <20171116154309.tfq5ix2hzwzci...@machine.or.cz>: > Hi, > > when explaining AlphaGo Zero to

Re: [Computer-go] Is MCTS needed?

2017-11-16 17:37 UTC+01:00, Gian-Carlo Pascutto : > Third, evaluating with a different rotation effectively forms an > ensemble that improves the estimate. Could you expand on that? I understand rotating the board has an impact for a neural network, but how does that change

Re: [Computer-go] Is MCTS needed?

Hi Petr, > What would you say is the current state-of-art game tree search for > chess? That's a very unfamiliar world for me, to be honest all I really > know is MCTS... Stockfish is one of the top-three chess programs, and it is open source. It is mainly iterative deepening alpha-beta, but

Re: [Computer-go] Is MCTS needed?

On 16/11/2017 16:43, Petr Baudis wrote: > But now, we expand the nodes literally all the time, breaking the > stationarity possibly in drastic ways. There are no reevaluations > that would improve your estimate. First of all, you don't expect the network evaluations to drastically vary between

Re: [Computer-go] Is MCTS needed?

As far as I know, the state of art in chess is some flavor of alphabeta (as long as I read stockfish source correctly), so basically they prove their current esimation is the best one up to a certain depth. MCTS has the benefit to enable various depth search depending on how good the evaluation