Sciweavers

515 search results - page 56 / 103
» Approximating Markov Processes by Averaging
Sort
View
NIPS
2007
15 years 7 months ago
Bayes-Adaptive POMDPs
Bayesian Reinforcement Learning has generated substantial interest recently, as it provides an elegant solution to the exploration-exploitation trade-off in reinforcement learning...
Stéphane Ross, Brahim Chaib-draa, Joelle Pi...
TSP
2008
151views more  TSP 2008»
15 years 6 months ago
Convergence Analysis of Reweighted Sum-Product Algorithms
Markov random fields are designed to represent structured dependencies among large collections of random variables, and are well-suited to capture the structure of real-world sign...
Tanya Roosta, Martin J. Wainwright, Shankar S. Sas...
GLOBECOM
2007
IEEE
16 years 13 days ago
ARMA Synthesis of Fading Channels- an Application to the Generation of Dynamic MIMO Channels
— Adaptive transceivers play an important role in wireless communications and the design of MIMO systems. Therefore models that enable simulation of dynamic and time varying chan...
Hani Mehrpouyan, Steven D. Blostein
ICML
2007
IEEE
16 years 7 months ago
Learning state-action basis functions for hierarchical MDPs
This paper introduces a new approach to actionvalue function approximation by learning basis functions from a spectral decomposition of the state-action manifold. This paper exten...
Sarah Osentoski, Sridhar Mahadevan
ICML
2006
IEEE
16 years 7 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