cs.AIMar 3, 2026

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

Authors: Mark Goadrich, Achille Morenville, Éric Piette

Organizations: Hendrix College, Conway AR 72032, USA · ICTEAM, UCLouvain, Louvain-la-Neuve, Belgium

Read PDF
Ask AI
Cite

Copy citation

DOINot available for this paper

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.

Figures & tables

GameGenreOriginDatePlayersDeckScoringInformationTricksSets/RunsTeams
AgramLast TrickNiger20003UniqueOne WinnerP, D✓  
BlackJackBankingFrance19301FrenchHigh Score    
Crazy EightsSheddingUSA19403FrenchLow ScoreP   
CribbageAddingEngland16002FrenchHigh ScoreP, T, S, D ✓ 
CuckooExchangeFrance14906FrenchOne LoserP, S, D   
EuchreEuchreUSA18204UniqueHigh ScoreP, T, S, D✓ ✓
Table 1: Valet includes twenty-one games that represent a variety of genres, the number of players, deck compositions, mechanics, and winning conditions, along with different methods of hiding and revealing information.
NameTypeDescription
PublicVisibilityCards are played face up, seen by all players.
HiddenVisibilityCards are played face down, unseen by players.
PrivateVisibilityCards are held by players to create private information.
BackVisibilityCards are distinguished by type, indicated on the back.
TakenMovementPublic cards are moved to private or hidden locations.
SharedMovementPrivate cards are moved to private or hidden locations.
Table 2: Card games hide and reveal information in different ways.
Figure 1: Information flow diagrams for six games in Valet.
Figure 2: The branching factor at each decision point of the game, summarized from 100 random rollouts. Each player is denoted with a different color. Since both axis are integers, an x-y jitter filter is used to help visualize the distributions.
Figure 3: The distribution of game lengths over 100 random rollouts for each game. The lengths of the game are on a logarithmic scale.
Figure 4: A violin plot of the distribution of scores for the first player in each game, comparing MCTS with random.

Explore similar work

CardsList

  1. BluffJAX: Adversarial Imperfect Information Games in JAX

    Oct 6, 2026Aryaman Reddi, Jan Peters, Carlo D'EramoImperfect-Information GamesRL Benchmarks

    Department of Computer Science, TU Darmstadt, Germany · Hessian Center for Artificial Intelligence (Hessian.ai), Germany · German Research Center for AI (DFKI), Systems AI for Robot Learning, Germany +1

  2. Unsound Search with Policy and Value Networks in Legends of Code and Magic

    Sep 6, 2026Dustin RubinGame-Playing AgentsImperfect-Information Games

    Georgia Institute of Technology Atlanta, Georgia, USA

  3. AV-AIVAT: 74x Cheaper Agent Evaluation with Certified Anytime-Valid Stopping in Imperfect-Information Games

    Aug 6, 2026Boning Li, Yu Chen, Longbo HuangEarly StoppingImperfect-Information Games

    IIIS, Tsinghua University