Skip to content

Latest commit

 

History

History
9 lines (5 loc) · 396 Bytes

README.md

File metadata and controls

9 lines (5 loc) · 396 Bytes

Implementation of Q-learning algorithm

  • The aim is to train the mouse as to be able to find the cheese with the best/closest path possible.

  • Comparision of a random selection and softmax selection can be seen from the pull-request report. Also the same results is avaiable in output files seperately.

  • There is also a .c version of the program without plots.

    • Mouse and Cheese