The main purpose of this assignment was to do coding for Reinforcement Learning with Python. The main objective of this assignment was to gain brief knowledge about Reinforcement Learning with Python.
In this experiment was included three parts which are practical the given code example, modelling the discussed example problem in the lecture note using Python and compare the output and results in Octave verse Python. And the third part was answered by modelling the Exercise problem of maze solving given in the lecture note. Jupiter notebook and Octave were used to analyze output and results. This software reduces the errors involved in experimenting as compared to those performed manually. This is because Colab notebook and Octave which lead to high precision and accuracy in the results obtained while analyzing outputs. In conclusion, Q-learning appears to be an intriguing idea and maybe considerably more entrancing than customary directed Artificial Intelligent since for this situation the machine is essentially gaining without any preparation how to play out a specific undertaking to enhance potential compensations