Category: Engines

New Atarigo bot

Do you think you are good at capture go (atarigo)? It is an easy game for beginners, right?

Now even a strong player can test their real skills at atarigo. Hactar go has got renewed server-based atarigo bot, “Capture GO master”.

“Capture GO master” bot has been trained using reinforcement learning, so the same technique the alphazero used. It is quite strong. To be honest I don’t know how strong it is, as I have not won the released version…

A new atarigo bot may not be world-shaking news for most of us. But internally it is a big step in creating new Hactar tools and renewing some of the old infrastructure.

Update to Katago networks

Distributed Katago training (https://katagotraining.org/) has produced a new improved network a while ago. The network is known by nice name “b18c384nbt”. I installed the network to Hactar servers a few days ago, and they seem to work fine.

Networs are about 20% faster than old ones used in Hactar server. At the same time networks are stronger that old networks. So Hactar should be now both a bit faster and a bit stronger!

Improvement in the network is due to a new structure of the network. New network is still learning faster that old network was, so I will probably update the network once their learning speed has settled.

Better 19×19 engine

Hactar is finally retiring well-served Pachi engine for 19×19 boards. The Pachi engine cannot meet modern expectations, where AI easily beats humans. The 9×9 and 13×13 bots are still be Pachi-based, they will be converted to new AI engine later.

New engine is combination of katago engine and a custom model for human-level play. This allows the bot to play very human-like game.

The custom model is trained using human games. As most games were bit older, it mostly plays with somewhat older style. The model seems to be quite good at tactics and ladders. So even if it is weaker than katago, it is not easy to trick.

I will be adjusting the engine further in following days.

Let me know how the new engine feels!

Update: The new engine still bit bad with white and high handicaps. So Pachi is still doing the job for high handicaps.

New engine playing

My first engine to play is now playing in 9×9 board. Engine is pretty typical AlphaZero trained engine with deep neural network. And name engine is Hactar, as this is intended for Hactar android app, although engine will be on cloud.

Currently engine is active on cgos bot server . At the moment Hactar is in 2nd  place among active bots, but in past there have been significantly stronger bots in the server. When Hactar is not playing anymore, past results can be found also from bayes estimation pages.

Engine is using one 1080ti card, CPU use is not significant.

The engine name “Hactar-7-181” contains also neural network model number (7) and the training iteration. For details of neural network and differences between versions, I will need to write another posting.

Creating new engine

Creating a go engine used to be a huge effort. After a basic program structure was in place, a lot of tuning was needed.

Since Deep neural Networks were adapted to go, creating a new engine has been a lot less work.

And since the AlphaZero go engine training technique, creating a strong go engine is not so much work, but awfully lot of GPU computing time.

So currently I am in progress of doing new engine for Hactar. This has progressed really well; I hope to be able to publish results really soon (still, do not hold your breath). The main challenge is to reduce the needed GPU time to something reasonable.