98 search results - page 2 / 20 » Using Rewards for Belief State Updates in Partially Observab... |
AAAI
1996
1996
Computing Optimal Policies for Partially Observable Decision Processes Using Compact Representations
13 years 6 months ago
: Partially-observable Markov decision processes provide a very general model for decision-theoretic planning problems, allowing the trade-offs between various courses of actions t...
COLING
2010
12 years 11 months ago
2010
This paper investigates how to automatically create a dialogue control component of a listening agent to reduce the current high cost of manually creating such components. We coll...
PKDD
2010
Springer
13 years 2 months ago
2010
Springer
Partially observable Markov decision processes (POMDPs) are widely used for planning under uncertainty. In many applications, the huge size of the POMDP state space makes straightf...
FOCS
2007
IEEE
13 years 11 months ago
2007
IEEE
We consider a variant of the classic multi-armed bandit problem (MAB), which we call FEEDBACK MAB, where the reward obtained by playing each of n independent arms varies according...
ECML
2005
Springer
13 years 10 months ago
2005
Springer
This paper examines the problem of finding an optimal policy for a Partially Observable Markov Decision Process (POMDP) when the model is not known or is only poorly specified. W...