Sciweavers

499 search results - page 40 / 100
» Model Minimization in Markov Decision Processes
Sort
View
ECBS
2009
IEEE
113views Hardware» more  ECBS 2009»
14 years 3 months ago
Modeling and Analysis of Probabilistic Timed Systems
Probabilistic models are useful for analyzing systems which operate under the presence of uncertainty. In this paper, we present a technique for verifying safety and liveness prop...
Abhishek Dubey, Derek Riley, Sherif Abdelwahed, Te...
NIPS
2007
13 years 10 months ago
Online Linear Regression and Its Application to Model-Based Reinforcement Learning
We provide a provably efficient algorithm for learning Markov Decision Processes (MDPs) with continuous state and action spaces in the online setting. Specifically, we take a mo...
Alexander L. Strehl, Michael L. Littman
ICC
2007
IEEE
121views Communications» more  ICC 2007»
14 years 3 months ago
Structure and Optimality of Myopic Sensing for Opportunistic Spectrum Access
We consider opportunistic spectrum access for secondary users over multiple channels whose occupancy by primary users is modeled as discrete-time Markov processes. Due to hardware...
Qing Zhao, Bhaskar Krishnamachari
ICAI
2009
13 years 6 months ago
The Utility of Affect in the Selection of Actions and Goals Under Real-World Constraints
We present a novel affective goal selection mechanism for decision-making in agents with limited computational resources (e.g., such as robots operating under real-time constraint...
Paul W. Schermerhorn, Matthias Scheutz
UAI
2000
13 years 10 months ago
Value-Directed Belief State Approximation for POMDPs
We consider the problem belief-state monitoring for the purposes of implementing a policy for a partially-observable Markov decision process (POMDP), specifically how one might ap...
Pascal Poupart, Craig Boutilier