State-of-the-art methods for solving 2-player zero-sum imperfect information games rely on
linear programming or regret minimization, though not on dynamic programming (DP) or …

The process of revising (or constructing) a policy at execution time--known as decision-time
planning--has been key to achieving superhuman performance in perfect-information games …

This study explores the intricate dynamics between player performance, reward frequency,
and unpredictability in gaming experiences within the context of game refinement theory. It …

A recent method for solving zero-sum partially observable stochastic games (zs-POSGs)
embeds the original game into a new one called the occupancy Markov game. This …

A recent theory suggests recasting common-payoff POSGs into non-observable problems
through the introduction of an appropriate statistic. Doing so offers additional levers to …