A Profit-Maximizing Reinforcement Learning-Based AI System in Python

Dr. Soper provides a complete example of a profit-maximizing artificial intelligence system in Python that relies on Thompson Sampling-based reinforcement learning to decide which advertising campaign to show to a company's customers. Each part of the Python source code and the corresponding results are discussed in detail to ensure understanding. Jupyter notebook for this lesson: https://colab.research.google.com/drive/1JXRGh6c8nVqMmw9gR1G0E3AzH67vqUp1 Previous lesson (Reinforcement Learning: Thompson Sampling & The Multi Armed Bandit Problem - Part 02): https://youtu.be/lDtVuJKLykQ Next lesson (Foundations of Q-Learning): https://youtu.be/__t2XRxXGxI