Date
Description
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
GUID
oai:openresearch-repository.anu.edu.au:10440/32
Handle
Identifier
oai:openresearch-repository.anu.edu.au:10440/32
Identifiers
Journal of Artificial Intelligence Research 25 (2006): 17-74
1076-9757
http://hdl.handle.net/10440/32
http://digitalcollections.anu.edu.au/handle/10440/32
https://openresearch-repository.anu.edu.au/bitstream/10440/32/3/Thiebaux_Decision2006.pdf.jpg
Publication Date
Titles
Decision-theoretic planning with non-Markovian rewards
Type