Reference : Stochastic POMDP controllers: How easy to optimize?
Scientific congresses, symposiums and conference proceedings : Unpublished conference
Engineering, computing & technology : Computer science
Stochastic POMDP controllers: How easy to optimize?
Vlassis, Nikos mailto [University of Luxembourg > Luxembourg Centre for Systems Biomedicine (LCSB) > >]
Littman, M. L. [> >]
Barber, D. [> >]
10th European Workshop on Reinforcement Learning
[en] Markov decision process ; POMDP ; stochastic controller ; computational complexity ; NP-hardness
[en] It was recently shown that computing an optimal stochastic controller in a discounted
in finite-horizon partially observable Markov decision process is an NP-hard problem. The
reduction (from the independent-set problem) involves designing an MDP with special
state-action rewards. In this note, we show that the case of state-only-dependent rewards
is also NP-hard.
Luxembourg Centre for Systems Biomedicine (LCSB): Machine Learning (Vlassis Group)

There is no file associated with this reference.

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.