Session
Reinforcement Learning Agents for Ayo: A Traditional Nigerian Game
Abstract:
Ayo, a traditional mancala-style game widely played in Nigeria, presents an intriguing challenge for artificial intelligence research. This study explores the application of various reinforcement learning algorithms to train agents capable of playing Ayo at a high level. By leveraging the rich cultural heritage of this game, we aim to showcase how AI can be harnessed to preserve and promote traditional African games while advancing the frontiers of machine learning research.
The project implements several reinforcement learning algorithms, including Monte Carlo Tree Search (MCTS), Minimax with alpha-beta pruning, and heuristic-based agents. These agents are evaluated through extensive simulations, providing insights into their performance and decision-making strategies. Additionally, a graphical user interface (GUI) is developed using the Tkinter library, enabling human players to engage with the trained agents and experience the dynamic gameplay of Ayo. This interactive component not only facilitates human-agent interactions but also serves as a platform for further research and experimentation.
The research findings contribute to the understanding of reinforcement learning techniques applied to traditional games and highlight the potential of AI in preserving and promoting cultural heritage. By presenting this work at the IndabaX Nigeria conference, we aim to foster discussions on the intersection of AI and cultural preservation, while showcasing the potential of AI-driven innovations for Nigeria's digital economy.
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top