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.
Mark Hammond is cofounder and CEO at Bonsai. Mark has a deep passion for understanding how the mind works and has been thinking about AI throughout his career. He has held positions at Microsoft and numerous startups and in academia, including turns at Numenta and in the Yale Neuroscience Department. He holds a degree in computation and neural systems from Caltech.
©2018, O'Reilly Media, Inc. • (800) 889-8969 or (707) 827-7019 • Monday-Friday 7:30am-5pm PT • All trademarks and registered trademarks appearing on oreilly.com are the property of their respective owners. • firstname.lastname@example.org