Sciweavers

267 search results - page 9 / 54
» Qualitative Analysis of Partially-Observable Markov Decision...
Sort
View
COLT
2000
Springer
13 years 12 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
ICRA
2007
IEEE
126views Robotics» more  ICRA 2007»
14 years 1 months ago
A formal framework for robot learning and control under model uncertainty
— While the Partially Observable Markov Decision Process (POMDP) provides a formal framework for the problem of robot control under uncertainty, it typically assumes a known and ...
Robin Jaulmes, Joelle Pineau, Doina Precup
AAAI
2007
13 years 10 months ago
Situated Conversational Agents
A Situated Conversational Agent (SCA) is an agent that engages in dialog about the context within which it is embedded. Situated dialog is characterized by its deep connection to ...
William Thompson
UAI
2003
13 years 9 months ago
Optimal Limited Contingency Planning
For a given problem, the optimal Markov policy over a finite horizon is a conditional plan containing a potentially large number of branches. However, there are applications wher...
Nicolas Meuleau, David E. Smith
CDC
2008
IEEE
140views Control Systems» more  CDC 2008»
14 years 2 months ago
Information state for Markov decision processes with network delays
We consider a networked control system, where each subsystem evolves as a Markov decision process (MDP). Each subsystem is coupled to its neighbors via communication links over wh...
Sachin Adlakha, Sanjay Lall, Andrea J. Goldsmith