Sciweavers

332 search results - page 45 / 67
» Ranking policies in discrete Markov decision processes
Sort
View
CDC
2008
IEEE
118views Control Systems» more  CDC 2008»
14 years 3 months ago
A density projection approach to dimension reduction for continuous-state POMDPs
Abstract— Research on numerical solution methods for partially observable Markov decision processes (POMDPs) has primarily focused on discrete-state models, and these algorithms ...
Enlu Zhou, Michael C. Fu, Steven I. Marcus
UAI
2000
13 years 10 months ago
Value-Directed Belief State Approximation for POMDPs
We consider the problem belief-state monitoring for the purposes of implementing a policy for a partially-observable Markov decision process (POMDP), specifically how one might ap...
Pascal Poupart, Craig Boutilier
ICML
2006
IEEE
14 years 10 months ago
Using inaccurate models in reinforcement learning
In the model-based policy search approach to reinforcement learning (RL), policies are found using a model (or "simulator") of the Markov decision process. However, for ...
Pieter Abbeel, Morgan Quigley, Andrew Y. Ng
ICML
2002
IEEE
14 years 10 months ago
Pruning Improves Heuristic Search for Cost-Sensitive Learning
This paper addresses cost-sensitive classification in the setting where there are costs for measuring each attribute as well as costs for misclassification errors. We show how to ...
Valentina Bayer Zubek, Thomas G. Dietterich
FLAIRS
2004
13 years 10 months ago
State Space Reduction For Hierarchical Reinforcement Learning
er provides new techniques for abstracting the state space of a Markov Decision Process (MDP). These techniques extend one of the recent minimization models, known as -reduction, ...
Mehran Asadi, Manfred Huber