Reinforcement learning (RL) implementation of imperfect information game Mahjong using markov decision processes to predict future game states
Watching my grandma play mahjong online and I was curious how the NPCs made their decisions.
Non-Player Characters (NPCs)
Computational Modelling
Game Aesthetics
Reinforcement Learning
Deep Neural Network
Deep Q-Learning
Q-table matrix that updates Q-table based on the Prediction of Future Mahjong States.
Q-values updated according to the Bellman Equation.