AI Agents for the Dhumbal Card Game: A Comparative Study
On the map: Deep reinforcement learning methods → RL for games and combinatorial optimization
Abstract (arXiv)
This study evaluates Artificial Intelligence (AI) agents for Dhumbal, a culturally significant multiplayer card game with imperfect information, through a systematic comparison of rule-based, search-based, and learning-based strategies. We formalize Dhumbal's mechanics and implement diverse agents, including heuristic approaches (Aggressive, Conservative, Balanced, Opportunistic), search-based methods such as Monte Carlo Tree Search (MCTS) and Information Set Monte Carlo Tree Search (ISMCTS), and reinforcement learning approaches including Deep Q-Network (DQN) and Proximal Policy Optimization (PPO), and a random baseline. Evaluation involves within-category tournaments followed by a cross-category championship. Performance is measured via win rate, economic outcome, Jhyap success, cards discarded per round, risk assessment, and decision efficiency. Statistical significance is assessed using Welch's t-test with Bonferroni correction, effect sizes via Cohen's d, and 95% confidence intervals (CI). Across 1024 simulated rounds, the rule-based Aggressive agent achieves the highest win rate (88.3%, 95% CI: [86.3, 90.3]), outperforming ISMCTS (9.0%) and PPO (1.5%) through effective exploitation of Jhyap declarations. The study contributes a reproducible AI framework, insights into heuristic efficacy under partial information, and open-source code, thereby advancing AI research and supporting digital preservation of cultural games.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods. Builds on 12 of its 23 references that are in the map. First posted on arXiv 10 Oct 2025.
Builds on
12 of 23 references.
References · 12
- 2017Proximal Policy Optimization Algorithmscited by 15,215
- 2019Mastering Atari, Go, Chess and Shogi by Planning with a Learned Modelcited by 1,353
- 2019QTRAN: Learning to Factorize with Transformation for Cooperative Multi-Agent Reinforcement Learningcited by 379
- 2021Mastering Atari Games with Limited Datacited by 237
- 2019The Hanabi Challenge: A New Frontier for AI Researchcited by 197
- 2016Deep Reinforcement Learning from Self-Play in Imperfect-Information Gamescited by 158
- 2020Combining Deep Reinforcement Learning and Search for Imperfect-Information Gamescited by 114
- 2021DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learningcited by 66
- 2019RLCard: A Toolkit for Reinforcement Learning in Card Gamescited by 35
- 2021Search in Imperfect Information Gamescited by 8
- 2021Evolving Evaluation Functions for Collectible Card Game AIcited by 6
- 2024PyTAG: Tabletop Games for Multi-Agent Reinforcement Learningcited by 2
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026"Pharos Night: Crown Pursuit": An AI-Native Deck-Building and Tactical Arena Game Design Based on Multi-Agent Systems
- 2024AlphaDou: High-Performance End-to-End Doudizhu AI Integrating Bidding
- 2026Can AI Agents Learn Their Way to the Top? Evaluating Heuristic Learning in a Long-Running Game Agent Competition
- 2025VGC-Bench: Towards Mastering Diverse Team Strategies in Competitive Pok'emon
- 2025Evaluating Language Models' Evaluations of Games
- 2024Dominion: A New Frontier for AI Research
- 2025Outbidding and Outbluffing Elite Humans: Mastering Liar's Poker via Self-Play and Reinforcement Learning
- 2025Mastering Da Vinci Code: A Comparative Study of Transformer, LLM, and PPO-based Agents