![]() CadiaPlayer has already proven its effectiveness by winning the 20 Association for the Advancement of Artificial Intelligence (AAAI) GGP competitions. Furthermore, we empirically evaluate different simulation-based approaches on a wide variety of games, introduce a domain-independent enhancement for automatically learning search-control knowledge to guide the simulation playouts, and show how to adapt the simulation searches to be more effective in single-agent games. In this paper, we describ e CadiaPlayer, a GGP agent employing a radically different approach: instead of a traditional game-tree search, it uses Monte Carlo simulations for its move decisions. The first successful GGP agents all followed that. ![]() ![]() The traditional design model for GGP agents has been to use a minimax-based game-tree search augmented with an automatically learned heuristic evaluation function. The aim of general game playing (GGP) is to create intelligent agents that can automatically learn how to play many different games at an expert level without any human intervention. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |