Decision-theoretic planning with non-Markovian rewards
A decision process in which rewards depend on history rather than merely on the current state is called a decision process with non-Markovian rewards (NMRDP). In decision-theoretic planning, where many desirable behaviours are more naturally expressed as
|Collections||ANU Research Publications|
|Source:||Journal of Artificial Intelligence Research|
|Thiebaux_Decision2006.pdf||682.74 kB||Adobe PDF|
Items in Open Research are protected by copyright, with all rights reserved, unless otherwise indicated.