Timeline for What does the Reward function depend on in a Markov Decision Processes (MDPs), in the context of Reinforcement Learning?

5 events

when toggle format	what		by	license	comment
Sep 12, 2023 at 15:04	comment	added	Rémy Hosseinkhan Boucher		@PierreLison do you have any reference on the equivalence of algorithms under those different design ?
Jan 11, 2015 at 16:05	comment	added	Pierre Lison		It's not really that one representation is "faster" or "more accurate" than another. It's more than the type of function depends on the domain you are trying to model. For instance, if you simply want to encode in your reward function that some states are "good" (goal states) while others are "bad" (failure states), then the easiest is to encode the reward function as R(s). But if the reward also depend on the system action, then the function R(s,a) is to be preferred. Finally, if the resulting state s' should also be accounted for when determining the reward, R(s,a,s') is best.
Jan 10, 2015 at 21:19	comment	added	Charlie Parker		Basically, it comes down to a modeling choice right? Depending on what actually is feasible to learn? If say R(s,a) is too slow and R(s) is much faster, even if its less accurate, we might choose R(s)? Right? Its basically a choice depending on the application?
Jan 10, 2015 at 21:18	vote	accept	Charlie Parker
Aug 28, 2014 at 9:55	history	answered	Pierre Lison	CC BY-SA 3.0