-
R2-B2: Recursive Reasoning-Based Bayesian Optimization for No-Regret Learning...
The dataset used in the paper is a synthetic game with two agents, where the payoff functions are sampled from a Gaussian process. -
Bounds for Approximate Regret-Matching Algorithms
The dataset used in the paper is a large imperfect-information game, and the authors used it to test their approximate regret-matching algorithm.
