# What are some approaches to estimate the transition and observation probabilities in POMDP?

What are some common approaches to estimate the transition or observation probabilities, when the probabilities are not exactly known?

When realizing a POMDP model, the state model needs additional information in terms of transition and observation probabilities. Often these probabilities are not known and an equal distribution is also not given. How can we proceed?

• I had asked a more general but very similar question here a long time ago.
– nbro
Sep 18 '20 at 13:26