Relative Content

Tag Archive for pythonartificial-intelligencereinforcement-learningq-learning

Rewards value not updating

I am trying to create a Q learning maze that solves the maze and uses a rewards system where hitting the wall is -1 and finishing is 100, however, when I reach the goal, my total rewards are always 100 regardless of how many walls I hit, how do I fix this problem? I tried adding print statements for when the values are updated but they never printed? I am not sure why? maze