Back to Results
First PageMeta Content
Stochastic control / Control theory / Partially observable Markov decision process / Monte Carlo POMDP / Markov decision process / Algorithm / Maximum likelihood / Statistics / Dynamic programming / Markov processes


Integrated Perception and Planning in the Continuous Space: A POMDP Approach Haoyu Bai David Hsu
Add to Reading List

Document Date: 2013-09-25 21:49:37

Open Document

File Size: 562,16 KB

Share Result on Facebook

Company

K. Hsiao L.P. / Neural Information Processing Systems / Robotics & Autonomous Systems / MIT Press / Coastal / US Air Force Research Laboratory / R. Tedrake L.P. / B. Intersection Navigation / /

Facility

University of Massachusetts Amherst / US Air Force Research Laboratory / Computer Science National University of Singapore Singapore / /

IndustryTerm

stochastic systems / Online search / online policy execution / reinforcement learning algorithms / policy search algorithm / forward search / Policy search / learning applications / /

Organization

National University of Singapore / 2010-T2-2-071 and National Research Foundation Singapore / MIT / Computer Science National University / POMDP Approach Haoyu Bai David Hsu Wee Sun Lee Department / University of Massachusetts Amherst / /

Person

R. Platt Jr / max B / David Hsu Wee Sun Lee / /

Position

high-fidelity model for vehicle navigation / finitestate controller / LQG-MP / /

Product

Theorem 4 / /

ProgrammingLanguage

V / C / K / /

PublishedMedium

Machine Learning / /

RadioStation

WAIT / /

Technology

POMDP algorithm / reinforcement learning algorithms / Online planning algorithms / return G0 Algorithm / belief space B. An offline POMDP algorithm / POMDP algorithms / Point-based POMDP algorithms / LGORITHM A. Overview Our algorithm / Machine Learning / simulation / policy search algorithm / /

SocialTag