Sciweavers

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

12

NIPS
2003

favoriteEmaildiscussreport

180views Information Technology» more NIPS 2003»

Bounded Finite State Controllers

13 years 5 months ago

Bounded Finite State Controllers

Download books.nips.cc

We describe a new approximation algorithm for solving partially observable MDPs. Our bounded policy iteration approach searches through the space of bounded-size, stochastic ﬁnite state controllers, combining several advantages of gradient ascent (efﬁciency, search through restricted controller space) and policy iteration (less vulnerability to local optima).

Pascal Poupart, Craig Boutilier

Real-time Traffic

NIPS 2003 | NIPS 2007 | Policy Iteration | Policy Iteration Approach | Stochastic ﬁnite State |

claim paper

Related Content

» Sparse Stochastic FiniteState Controllers for POMDPs

» FSMHume is finite state

» On Near Optimality of the Set of FiniteState Controllers for Average Cost POMDP

» Optimization over state feedback policies for robust control with constraints

» State Complexity of Union and Intersection of Finite Languages

» New Bounds for the Capacity Region of the FiniteState Multiple Access Channel

» New Results on SingleStep Power Control System in Finite State Markov Channel Power Contro...

» State Nullification of Switched Systems by Linear Output Feedback

» Automatic Derivation of Memoryless Policies and FiniteState Controllers Using Classical Pl...

Post Info
More Details (n/a)

Added	31 Oct 2010
Updated	31 Oct 2010
Type	Conference
Year	2003
Where	NIPS
Authors	Pascal Poupart, Craig Boutilier

Comments (0)