Sciweavers

Free Online Productivity Tools i2Speak i2Symbol i2OCR iTex2Img iWeb2Print iWeb2Shot i2Type iPdf2Split iPdf2Merge i2Bopomofo i2Arabic i2Style i2Image i2PDF iLatex2Rtf Sci2ools

13

ORL
2008

favoriteEmaildiscussreport

68views more ORL 2008»

On polynomial cases of the unichain classification problem for Markov Decision Processes

13 years 4 months ago

On polynomial cases of the unichain classification problem for Markov Decision Processes

Download www.ams.sunysb.edu

The unichain classification problem detects whether a finite state and action MDP is unichain under all deterministic policies. This problem is NP-hard [11]. This paper provides polynomial algorithms for the unichain classification for an MDP with either a state that is recurrent under all deterministic policies or with a state that is absorbing under some action.

Eugene A. Feinberg, Fenghsu Yang

Real-time Traffic

Deterministic Policies | ORL 2008 | Unichain Classification | Unichain Classification Problem |

claim paper

Related Content

» QuasiDeterministic Partially Observable Markov Decision Processes

» Quasi deterministic POMDPs and DecPOMDPs

» Policy teaching through reward function learning

» Predictive representations for policy gradient in POMDPs

Post Info
More Details (n/a)

Added	14 Dec 2010
Updated	14 Dec 2010
Type	Journal
Year	2008
Where	ORL
Authors	Eugene A. Feinberg, Fenghsu Yang

Comments (0)