This is another post on Q-learning reinforcement algorithm. Here we will understand and implement the Knight & Princess problem from the scratch using Python language, where the Knight need to move to the place of Princess ignoring the enemies on its way. In this post I have not used any third party library such as gym. Read more…
Tag: reinforcement learning
Understanding Q-learning algorithm with example using Python
Q-learning is a reinforcement learning technique in Machine learning used to answer the question “what action to take under what circumstances”. This model-free machine learning technique is used mainly in implementing any finite Markov Decision Process. The application of reinforcement learning technique can be found in traffic light control, robotics, recommendation system, gaming etc.
Before knowing Q-learning algorithm, let’s first understand the motivation behind this. What kind questions can be answered by Q-learning algorithm? Read more…