Recently I played around with the Counterfactual Regret Minimization algorithm combined with neural networks. I managed to get a bot that plays recently well at Liar's Dice.
I also made a website so you can try your luck against it at https://dudo.ai
I wanted to write a blogpost describing the details of the algorithm as well as how you can measure the convergence to the optimal Nash Equilibrium strategy.
3 comments
[ 186 ms ] story [ 363 ms ] threadI also made a website so you can try your luck against it at https://dudo.ai
I wanted to write a blogpost describing the details of the algorithm as well as how you can measure the convergence to the optimal Nash Equilibrium strategy.