Hide/Show Apps

Learning a partially-observable card game hearts using reinforcement learning

Demirdöver, Buğra Kaan
Artificial intelligence and machine learning are widely popular in many sectors. Oneof them is the gaming industry. With many different scenarios, different types, gamesare perfect for machine learning and artificial intelligence. This study aims to developlearning agents to play the game of Hearts. Hearts is one of the most popular cardgames in the world. It is a trick based, imperfect information card game. In additionto having a huge state space, hearts offers many extra challenges due to the nature ofthe game. These challenges are divided into smaller parts where learning is easier andassigned to different learning agents. These agents use temporal difference learningto learn assigned parts.