Sciweavers

89 search results - page 2 / 18
» Action-Space Partitioning for Planning
Sort
View
AIPS
2011
13 years 1 months ago
Sample-Based Planning for Continuous Action Markov Decision Processes
In this paper, we present a new algorithm that integrates recent advances in solving continuous bandit problems with sample-based rollout methods for planning in Markov Decision P...
Christopher R. Mansley, Ari Weinstein, Michael L. ...
AAAI
2011
12 years 9 months ago
Policy Gradient Planning for Environmental Decision Making with Existing Simulators
In environmental and natural resource planning domains actions are taken at a large number of locations over multiple time periods. These problems have enormous state and action s...
Mark Crowley, David Poole
ICRA
2005
IEEE
118views Robotics» more  ICRA 2005»
14 years 3 months ago
Planning with Continuous Actions in Partially Observable Environments
Abstract— We present a simple randomized POMDP algorithm for planning with continuous actions in partially observable environments. Our algorithm operates on a set of reachable b...
Matthijs T. J. Spaan, Nikos A. Vlassis
ICTAI
2003
IEEE
14 years 3 months ago
Partitioning of Temporal Planning Problems in Mixed Space Using the Theory of Extended Saddle Points
We study the partitioning of temporal planning problems formulated as mixed-integer nonlinear programming problems, develop methods to reduce the search space of partitioned subpr...
Benjamin W. Wah, Yixin Chen
AIED
2011
Springer
13 years 1 months ago
Faster Teaching by POMDP Planning
Both human and automated tutors must infer what a student knows and plan future actions to maximize learning. Though substantial research has been done on tracking and modeling stu...
Anna N. Rafferty, Emma Brunskill, Thomas L. Griffi...