Sciweavers

168 search results - page 1 / 34
» Reinforcement Learning Algorithm for Partially Observable Ma...
Sort
View
COLT
2000
Springer
13 years 8 months ago
Estimation and Approximation Bounds for Gradient-Based Reinforcement Learning
We model reinforcement learning as the problem of learning to control a Partially Observable Markov Decision Process (  ¢¡¤£¦¥§  ), and focus on gradient ascent approache...
Peter L. Bartlett, Jonathan Baxter
ECML
2005
Springer
13 years 10 months ago
Active Learning in Partially Observable Markov Decision Processes
This paper examines the problem of finding an optimal policy for a Partially Observable Markov Decision Process (POMDP) when the model is not known or is only poorly specified. W...
Robin Jaulmes, Joelle Pineau, Doina Precup
ICML
1994
IEEE
13 years 7 months ago
Learning Without State-Estimation in Partially Observable Markovian Decision Processes
Reinforcement learning (RL) algorithms provide a sound theoretical basis for building learning control architectures for embedded agents. Unfortunately all of the theory and much ...
Satinder P. Singh, Tommi Jaakkola, Michael I. Jord...