The Update-Equivalence Framework for Decision-Time Planning

arXiv:2304.13138v2 Announce Type: replace-cross
Abstract: 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 like chess and Go. A recent line of work has extended decision-time planning to imperfect-information games, leading to superhuman performance in poker. However, these methods involve solving subgames whose sizes grow quickly in the amount of non-public information, making them unhelpful when the amount of non-public information is …

abstract arxiv chess cs.ai cs.lg decision framework games information key line performance planning poker policy process superhuman type update work