Backgammon Game Player using Artificial Intelligence
University of Washington, Seattle
09/2020 - 06/2021
Keywords: Artificial Intelligence, Reinforcement Learning, Expectiminimax Search Algorithm, Alpha-beta Pruning, Backgammon Game, Python
Role
Impacts
Skills
Descriptions
We implemented a Backgammon gameplay agent using reinforcement learning. The backbone algorithm of the agent is expectiminimax search with alpha-beta pruning to maintain its effeciency. Within the algorithm, we incorporated several factors in evaluating the state of the boards. For example, a racing strategy was implemented to check how far away the checkers are from their respective homebase. A few more strategies (bearoff, hitting, stacking, and making primes) were also used in our reinforcement decision factors.