Marc Lanctot

Hi @i-Madsen, thanks for the updates! Can you pull changes from master and merge them into your branch? I had to make some cosmetic changes to your code to adhere...

Also, note: I will soon not have access to the Internet for the next 8-10 days.. so apologies for any delays in responses.

Hi @i-Madsen, Ok the CI is fixed now as of https://github.com/google-deepmind/open_spiel/pull/1250 Can you pull from master and push the merge commit?

> @lanctot Ok, should be merged now. Ok seems there are some test failures for legitimate reasons (a function is marked void but I guess it's returning a bool?) Can...

I am sorry but we can't help. Unfortunately the original authors are not responding to questions regarding R-NaD, so it is currently is unmaintained. We will mark it as such...

Quick follow up. There is no guarantee that the loss is correlated with NashConv. These are neural networks, and small changes in loss can lead to quite different policies, especially...

Hi @Brunozml , Apologies for the lag in communication. I am currently travelling and will be away at a conference until mid May. The tic-tac-toe QLearner example is probably using...

Wow, cool to see the nice graphics @Brunozml @giogix2 ! I will change the docs to advertise pyspiel_game more prominently, it looks great! Ok, these are non-trivial questions. 1a. Deep...

As a follow-up to 1, instead of DREAM or ARMAC I suggest trying R-NaD (in this repos), which is the Friction FoReL algorithm behind the Mastering Stratego paper... or MMD...

@giogix2 Cool, yes I'd love to hear about more developments in pygame_spiel and would be happy to advertise its use on our development page (in fact I will do that...