Sciweavers

252 search results - page 11 / 51
» Learning Partially Observable Action Models: Efficient Algor...
Sort
View
UAI
2001
15 years 1 months ago
The Optimal Reward Baseline for Gradient-Based Reinforcement Learning
There exist a number of reinforcement learning algorithms which learn by climbing the gradient of expected reward. Their long-run convergence has been proved, even in partially ob...
Lex Weaver, Nigel Tao
CVPR
2009
IEEE
16 years 6 months ago
Learning to Track with Multiple Observers
We propose a novel approach to designing algorithms for object tracking based on fusing multiple observation models. As the space of possible observation models is too large for...
Björn Stenger, Roberto Cipolla, Thomas Woodle...
ICML
2000
IEEE
16 years 14 days ago
Learning Probabilistic Models for Decision-Theoretic Navigation of Mobile Robots
Decision-theoretic reasoning and planning algorithms are increasingly being used for mobile robot navigation, due to the signi cant uncertainty accompanying the robots' perce...
Daniel Nikovski, Illah R. Nourbakhsh
AAAI
2000
15 years 1 months ago
Back to the Future for Consistency-Based Trajectory Tracking
Given a model of a physical process and a sequence of commands and observations received over time, the task of an autonomous controller is to determine the likely states of the p...
James Kurien, P. Pandurang Nayak
ICRA
2007
IEEE
126views Robotics» more  ICRA 2007»
15 years 6 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