Q-Learning (Reinforcement learning): Bellman Equation, Markov Decision Processes, Q-Values, and…
中文摘要
本文探讨Q学习及其核心概念（贝尔曼方程、MDP和Q值），旨在解决非预测性的现实问题。
English Summary
This article explains Q-Learning and its fundamentals, including the Bellman Equation, MDPs, and Q-Values, to solve non-predictive real-world problems.
原文节选
Machine learning models are excellent at making predictions. However, many real-world problems are not prediction problems. Continue reading on Medium »