Solving risk-sensitive POMDPs with and without cost observations
Partially Observable Markov Decision Processes (POMDPs) are often used to model planning problems under uncertainty. The goal in Risk-Sensitive POMDPs (RS-POMDPs) is to find a policy that maximizes the probability that the cumulative cost is within some user-defined cost threshold. In this paper, un...
Saved in:
Main Authors: | HOU, Ping, YEOH, William, Pradeep VARAKANTHAM |
---|---|
Format: | text |
Language: | English |
Published: |
Institutional Knowledge at Singapore Management University
2016
|
Subjects: | |
Online Access: | https://ink.library.smu.edu.sg/sis_research/3605 https://ink.library.smu.edu.sg/context/sis_research/article/4606/viewcontent/RSPOMDP.pdf |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Singapore Management University |
Language: | English |
Similar Items
-
Prioritized Shaping of Models for Solving DEC-POMDPs
by: VARAKANTHAM, Pradeep Reddy, et al.
Published: (2012) -
Adaptive decision support for structured organizations: A case for OrgPOMDPs
by: VARAKANTHAM, Pradeep Reddy, et al.
Published: (2011) -
Implementation Techniques for Solving POMDPs in Personal Assistant Domains
by: VARAKANTHAM, Pradeep Reddy, et al.
Published: (2006) -
Revisiting Risk-Sensitive MDPs: New Algorithms and Results
by: HOU, Ping, et al.
Published: (2014) -
Offline RL with discrete proxy representations for generalizability in POMDPs
by: GU, Pengjie, et al.
Published: (2023)