Sciweavers

98 search results - page 13 / 20
» Using Rewards for Belief State Updates in Partially Observab...
Sort
View
NIPS
2001
13 years 9 months ago
Predictive Representations of State
We show that states of a dynamical system can be usefully represented by multi-step, action-conditional predictions of future observations. State representations that are grounded...
Michael L. Littman, Richard S. Sutton, Satinder P....
DATE
2008
IEEE
136views Hardware» more  DATE 2008»
14 years 2 months ago
A Framework of Stochastic Power Management Using Hidden Markov Model
- The effectiveness of stochastic power management relies on the accurate system and workload model and effective policy optimization. Workload modeling is a machine learning proce...
Ying Tan, Qinru Qiu
IROS
2006
IEEE
121views Robotics» more  IROS 2006»
14 years 1 months ago
Planning and Acting in Uncertain Environments using Probabilistic Inference
— An important problem in robotics is planning and selecting actions for goal-directed behavior in noisy uncertain environments. The problem is typically addressed within the fra...
Deepak Verma, Rajesh P. N. Rao
UAI
2004
13 years 9 months ago
Region-Based Incremental Pruning for POMDPs
We present a major improvement to the incremental pruning algorithm for solving partially observable Markov decision processes. Our technique targets the cross-sum step of the dyn...
Zhengzhu Feng, Shlomo Zilberstein
AAAI
2008
13 years 10 months ago
A Variance Analysis for POMDP Policy Evaluation
Partially Observable Markov Decision Processes have been studied widely as a model for decision making under uncertainty, and a number of methods have been developed to find the s...
Mahdi Milani Fard, Joelle Pineau, Peng Sun