Towards a Time-Aware Hidden Markov Model for the Truco Game

• Joaquim Assunção UFSM
• Gustavo Bathu Paulus IFRS

DOI: https://doi.org/10.5753/sbgames_estendido.2022.225638

Resumo

Similar to Poker, the game of Truco has challenges for Artificial intelligence. Considering a large number of game states, a scenario characterized by partial visibility, stochastic behavior, and score susceptible to bluff; this game offers a good set of rules to test and improve AI techniques. In this article, we describe the creation of a Hidden Markov Model (HMM) agent using temporal control. The model has an embedded vector that adjusts its probabilities for further game actions, consequently, improving the model playing performance. The evaluation is given with over 210,000 matches, serving as empirical proof of the idea.

Palavras-chave: HMM, time-aware, games, Truco

Referências

Moral, R. C., Paulus, G. B., Assunção, J. V., and Silva, L. A. (2020). Investigating case learning techniques for agents to play the card game of truco. In 2020 19th Brazilian Symposium on Computer Games and Digital Entertainment (SBGames), pages 107– 116. IEEE.

Niklaus, J., Alberti, M., Pondenkandath, V., Ingold, R., and Liwicki, M. (2019). In Survey of Artificial Intelligence for Card Games and Its Application to the Swiss Game Jass, pages 25–30.

Paulus, G. B., C. Assuncao, J. V., and Silva, L. A. L. (2019). Cases and clusters in reuse policies for decision-making in card games. In 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI), pages 1361–1365.

Richter, M. and Weber, R. (2013). Case-Based Reasoning: A Textbook. Springer Berlin Heidelberg.

Rossato, L., Silva, L., and Assunção, J. (2020). A markovian model for the game of truco. In2020 19th Brazilian Symposium on Computer Games and Digital Entertainment (SBGames).

Rubin, J. and Watson, I. (2012). Case-based strategies in computer poker. AI communications, 25(1):19–48.

Stewart, W. J. (2009). Probability, Markov Chains, Queues, and Simulation: The Mathematical Basis of Performance Modeling. Princeton University Press.

Vargas, D. P., Paulus, G. B., and Silva, L. A. (2021). Active learning and case-based reasoning for the deceptive play in the card game of truco. In Brazilian Conference on Intelligent Systems, pages 313–327. Springer.

Zucchini, W., MacDonald, I., and Langrock, R. (2017). Hidden Markov Models for Time Series: An Introduction Using R, Second Edition. Chapman & Hall/CRC Monographs on Statistics and Applied Probability. CRC Press.