I've been researching different frameworks for hierarchical RL (mainly options, HAMs, and MAXQ) and noticed that both options and HAMs have names that relate to how they function. I can't seem to find anything stating how MAXQ got its name and I was wondering if anyone knew what the name was referencing.
Asked
Active
Viewed 39 times
2
-
Hello. Have you already looked at the MAXQ paper? The answer probably lies there. If you find the answer to your own question, feel free to write a formal answer below, so that future readers can also see it. – nbro Mar 07 '21 at 11:08