Reinforcement learning unchained: How to leverage machine teaching to build AI into complex, real-world systems

Description

Building complex, real-world reinforcement learning systems requires leveraging techniques such as curriculum learning, hierarchical RL, and reward shaping. Without using these and other techniques to guide the learning, you can easily obtain irreproducible policies with odd behavior or fail to converge on a policy altogether. Machine teaching collects these techniques together, allowing you to formally codify how to teach effective policies leveraging subject-matter expertise and programming.

Mark Hammond explores many of these techniques and illustrates how they can be effectively combined into a comprehensive machine teaching program.