23NPCS

We were eager of the idea of creating a competitive poker bot that could respond to other opposing players and create calculated movements to win. Our bot uses Monte Carlo simulations and heuristic algorithms to evaluate the strength of a hand and determine the optimal strategy to bet in real poker tournaments. We developed the bot in Python using the eval7 library to evaluate the hand and integrated Monte Carlo simulations with fixed betting thresholds and aggressive bet sizing to simulate realistic gameplay against opponents. This project required us to create multiple simulations to make a bot with the highest accuracy as well as managing under strict time constraints. We built a robust bot that consistently makes informed decisions under pressure and performs competitively against other enhanced poker bots. We learned the importance of integrating statistical modeling with strategic heuristics, the power of iterative testing and refinement, and valuable insights in game theory and decision-making. Our next steps include incorporating machine learning to create dynamic strategies to further enhance our bot’s performance in real-world competitive environments.