GitHub - khuang9/Snowball-Qlearning

Branches Tags

Name		Name	Last commit message	Last commit date
Latest commit History 2 Commits
QSnow.py		QSnow.py
readme.txt		readme.txt

Repository files navigation

This program takes in certain information for a snowball game and gives back a certain move using reinforcement learning.

The Q-table is updated based on the following Q-learning reward formula:
----------------------------
Q[player_to_index(prevState[0:3])][player_to_index(prevState[3:])][trainingMoveIndex] += learningRate * (reward + discountFactor * max(Q[player_to_index(currentTrainingState[0:3])][player_to_index(currentTrainingState[3:])]) - Q[player_to_index(prevState[0:3])][player_to_index(prevState[3:])][trainingMoveIndex])
----------------------------