I was reading a book about Dec-POMDPs and came across this curious result where the author specifies the number of possible joint policies to evaluate and the time needed to evaluate a single joint policy but I can understand how he got to these results.

Can anyone please help me understand the logic used here?enter image description here

Source: "Reinforcement Learning: State-of-the-Art", Editors Dr. Marco Wiering & Dr. ir. Martijn van Otterlo Radboud, DOI 10.1007/978-3-642-27645-3, Springer-Verlag Berlin Heidelberg 2012.

  • $\begingroup$ What book were you reading? What don't you understand specifically and what you understand? Edit your post to include this info. Moreover, reformulate the title in the form of a question. Thanks. $\endgroup$
    – nbro
    Jun 20, 2022 at 17:03
  • $\begingroup$ Which part of the argument in the source are you having trouble with? $\endgroup$
    – mikkola
    Jun 21, 2022 at 15:16


You must log in to answer this question.

Browse other questions tagged .