Learning to play an imperfect information card game using reinforcement learning

Demirdover B. K., BAYKAL Ö., Alpaslan F.

TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES, cilt.30, sa.6, ss.2303-2318, 2022 (SCI-Expanded) identifier identifier identifier

  • Yayın Türü: Makale / Tam Makale
  • Cilt numarası: 30 Sayı: 6
  • Basım Tarihi: 2022
  • Doi Numarası: 10.55730/1300-0632.3940
  • Dergi Adı: TURKISH JOURNAL OF ELECTRICAL ENGINEERING AND COMPUTER SCIENCES
  • Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED), Scopus, Academic Search Premier, Applied Science & Technology Source, Compendex, Computer & Applied Sciences, INSPEC, TR DİZİN (ULAKBİM)
  • Sayfa Sayıları: ss.2303-2318
  • Anahtar Kelimeler: Artificial intelligence, machine learning, reinforcement learning, supervised learning, neural networks, GO, SHOGI, CHESS
  • Orta Doğu Teknik Üniversitesi Adresli: Evet

Özet

Artificial intelligence and machine learning are widely popular in many areas. One of the most popular ones is gaming. Games are perfect testbeds for machine learning and artificial intelligence with various scenarios and types. This study aims to develop a self-learning intelligent agent to play the Hearts game. Hearts is one of the most popular trick-taking card games around the world. It is an imperfect information card game. In addition to having a huge state space, Hearts offers many extra challenges due to its nature. In order to ease the development process, the agent developed in the scope of this study was divided into subagents such that each subagent was assigned a part of the game. The experiment results reveal that the developed agent can compete against some rule based Hearts agents and human Hearts players.