muzero-general VS mage

I went looking for MuZero implementations in order to see how, exactly, they interact with the game space. Based on this one, which had the most stars in the muzero topic, it appears that it needs to be able to discern legal next steps from the current game state https://github.com/werner-duvaud/muzero-general/blob/master/...

So, I guess for the cards Forge has implemented one could MuZero it, but I believe it's a bit chicken and egg with a "free text" game like M:TG -- in order to train one would need to know legal steps for any random game state, but in order to have legal steps one would need to be able to read and interpret English rules and card text

You may want to use the trick described in https://arxiv.org/pdf/1805.11593.pdf as a Transformed Bellman Operator. Its efficiency is proved in MuZero original paper https://arxiv.org/pdf/1911.08265.pdf Appendix F. The implementation of that method you can find here: https://github.com/werner-duvaud/muzero-general Usage: muzero/models.py:649 (def support_to_scalar)

I have used this implementation from MuZero: https://github.com/werner-duvaud/muzero-general

+1 to taking a look at OpenSpiel. It has AlphaZero in C++ and Python, and there is even a PR open that allows running UCI (e.g. Stockfish) bot. You can also load chess via the OpenSpiel wrapper in muzero-general: https://github.com/werner-duvaud/muzero-general

When I looked up some community implementations, like that of Werner Duvaud on GitHub and Discord, hoping to make my own contributions to this effect, I soon found that I was hopelessly out of my depth as an amateur programmer, even with the help of some other sources like this walkthrough series. However, from what I could tell, most of the people working on this sort of thing seemed to be tackling relatively simple games. At first I thought this might be largely due to limitations in hobby time or computing power available to these users, but then I also noticed that, unless I have misunderstood something, it seems like the games are required to be rebuilt entirely in the engine of (this implementation of) MuZero, which would also obviously be a limit on the complexity of games chosen.

Windows support (Experimental / Workaround: Use the notebook in Google Colab)

There are several if you google "muzero github", e.g. https://github.com/werner-duvaud/muzero-general

Yeah, that surprised me too, given that https://github.com/magefree/mage is open source and pretty actively developed.

The project you want is http://xmage.today/

All cards available, and full rules engine.

My guess is that fully modeling MtG's rules in Datalog would take a lot more work, because MtG's rules are a lot more complex. Looking through the source for one of the freely-available game engines like https://github.com/magefree/mage would probably be more informative, though.

There's a draft every day, with events at different starting times to accommodate players from around the world, plus asynchronous side events including Rich Draft, Team Sealed, and Rotisserie Draft. We play on XMage which has full rules enforcement like MTGO but is 100% free software.

If you can tolerate some of its shortcomings, you can draft against bots on Xmage.

https://github.com/magefree/mage/issues is a more reliable place to report - this might not be a trivial fix

Update: My problem happened because the launcher had reverted to the non-beta xmage home address on its own. You probably have the same problem. You need to go to settings, set branch to custom, and the xmage home address to http://xmage.today/

Real life example: The open source implementation of MTG card game multiplayer