1 views collected around this technical thread.
This article explores the appeal of collecting cards in strategy‑focused trading and collectible card games, examining the distinction between physical TCGs and digital CCGs, the three core pleasures of card games, and how designers balance rarity, value, and gameplay experience.
DouZero, a reinforcement‑learning AI for the Chinese card game Dou Dizhu, combines a Monte‑Carlo value‑network with compact action encoding, trains on a four‑GPU server, and outperforms existing AI baselines, ranks first on Botzone, and even surpasses human play in several metrics.
The paper presents DouZero, a reinforcement‑learning AI for the Chinese card game Dou Dizhu that combines a Monte‑Carlo method with a value network, uses binary matrix encodings for states and actions, and achieves human‑level play and state‑of‑the‑art results on modest GPU hardware.