Foundations of Q-Learning

Dr. Soper discusses the foundations of Q-learning, which is one of the major types of reinforcement learning within the broader realm of artificial intelligence and cognitive computing systems. Topics of discussion include what Q-learning is, characteristics of Q-learning models, what Q-values are, what temporal differences are, what the Bellman Equation is, and how the Q-learning process works.

Previous lesson (A Profit-Maximizing Reinforcement Learning-Based AI System in Python):    • A Profit-Maximizing Reinforcement Lea...  
Next lesson (Q-Learning: A Complete Example in Python):    • Q-Learning: A Complete Example in Python