Research

Paper

AI LLM March 03, 2026

Valet: A Standardized Testbed of Traditional Imperfect-Information Card Games

Authors

Mark Goadrich, Achille Morenville, Éric Piette

Abstract

AI algorithms for imperfect-information games are typically compared using performance metrics on individual games, making it difficult to assess robustness across game choices. Card games are a natural domain for imperfect information due to hidden hands and stochastic draws. To facilitate comparative research on imperfect-information game-playing algorithms and game systems, we introduce Valet, a diverse and comprehensive testbed of 21 traditional imperfect-information card games. These games span multiple genres, cultures, player counts, deck structures, mechanics, winning conditions, and methods of hiding and revealing information. To standardize implementations across systems, we encode the rules of each game in RECYCLE, a card game description language. We empirically characterize each game's branching factor and duration using random simulations, reporting baseline score distributions for a Monte Carlo Tree Search player against random opponents to demonstrate the suitability of Valet as a benchmarking suite.

Metadata

arXiv ID: 2603.03252
Provider: ARXIV
Primary Category: cs.AI
Published: 2026-03-03
Fetched: 2026-03-04 03:41

Related papers

Raw Data (Debug)
{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2603.03252v1</id>\n    <title>Valet: A Standardized Testbed of Traditional Imperfect-Information Card Games</title>\n    <updated>2026-03-03T18:46:47Z</updated>\n    <link href='https://arxiv.org/abs/2603.03252v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2603.03252v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>AI algorithms for imperfect-information games are typically compared using performance metrics on individual games, making it difficult to assess robustness across game choices. Card games are a natural domain for imperfect information due to hidden hands and stochastic draws. To facilitate comparative research on imperfect-information game-playing algorithms and game systems, we introduce Valet, a diverse and comprehensive testbed of 21 traditional imperfect-information card games. These games span multiple genres, cultures, player counts, deck structures, mechanics, winning conditions, and methods of hiding and revealing information. To standardize implementations across systems, we encode the rules of each game in RECYCLE, a card game description language. We empirically characterize each game's branching factor and duration using random simulations, reporting baseline score distributions for a Monte Carlo Tree Search player against random opponents to demonstrate the suitability of Valet as a benchmarking suite.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.AI'/>\n    <published>2026-03-03T18:46:47Z</published>\n    <arxiv:comment>12 pages, 1 table, 4 figures</arxiv:comment>\n    <arxiv:primary_category term='cs.AI'/>\n    <author>\n      <name>Mark Goadrich</name>\n    </author>\n    <author>\n      <name>Achille Morenville</name>\n    </author>\n    <author>\n      <name>Éric Piette</name>\n    </author>\n  </entry>"
}