Learn about the technical foundations and recent developments of Q* (Q-star) in this 20-minute educational video that demystifies complex reinforcement learning concepts. Explore the evolution from basic Q-functions to advanced Q* applications, covering fundamental topics like Bellman equations, Markov Decision Processes, and entropy-based reinforcement learning. Delve into recent developments including Residual Q-Learning, policy customization, and maximum entropy policies, with particular focus on collaborative work between OpenAI and UC Berkeley. Gain clear explanations of how Q* relates to physics principles and agent behavior through imitation learning, dispelling common misconceptions about its connection to artificial general intelligence (AGI). Master technical concepts through structured segments that progress from basic Q-functions to advanced applications in maximum entropy reinforcement learning.