In recent years, Game AI research has made important breakthroughs using Reinforcement Learning (RL). Despite this, RL for modern tabletop games has gained little to no attention, even when they offer a range of unique challenges compared to video games. To bridge this gap, we introduce PyTAG, a Python API for interacting with the Tabletop Games framework (TAG). TAG contains a growing set of more than 20 modern tabletop games, with a common API for AI agents. We present techniques for training RL agents in these games and introduce baseline results after training Proximal Policy Optimisation algorithms on a subset of games. Finally, we discuss the unique challenges complex modern tabletop games provide, now open to RL research through PyTAG.

As a social bot, Microsoft's Zo is always available to play or talk on select platforms where people message and chat. Now, Exploding Kittens, the history-making card game that became an award-winning app, is turning to Microsoft's Zo to offer its first single-player version for fans. On Wednesday, Microsoft and the team behind Exploding Kittens announced a new, free version of the popular, award-winning game, which users can play one on one with Zo. Currently, it's being made available exclusively by chatting with Zo through Facebook Messenger (m.me/Zo), kik (kik.me/zo.ai) To play, start a conversation with Zo and ask if she'd like to play Exploding Kittens by texting "play EK".