Sciweavers

1138 search results - page 74 / 228
» Feature Markov Decision Processes
Sort
View
115
Voted
AAAI
2010
15 years 2 months ago
Compressing POMDPs Using Locality Preserving Non-Negative Matrix Factorization
Partially Observable Markov Decision Processes (POMDPs) are a well-established and rigorous framework for sequential decision-making under uncertainty. POMDPs are well-known to be...
Georgios Theocharous, Sridhar Mahadevan
ICMLA
2008
15 years 2 months ago
Prediction-Directed Compression of POMDPs
High dimensionality of belief space in Partially Observable Markov Decision Processes (POMDPs) is one of the major causes that severely restricts the applicability of this model. ...
Abdeslam Boularias, Masoumeh T. Izadi, Brahim Chai...
94
Voted
FLAIRS
2006
15 years 2 months ago
Stochastic Deliberation Scheduling using GSMDPs
We propose a new decision-theoretic approach for solving execution-time deliberation scheduling problems using recent advances in Generalized Semi-Markov Decision Processes (GSMDP...
Kurt D. Krebsbach
101
Voted
IJCAI
2001
15 years 2 months ago
Symbolic Dynamic Programming for First-Order MDPs
We present a dynamic programming approach for the solution of first-order Markov decisions processes. This technique uses an MDP whose dynamics is represented in a variant of the ...
Craig Boutilier, Raymond Reiter, Bob Price
103
Voted
ML
2002
ACM
121views Machine Learning» more  ML 2002»
15 years 10 days ago
Near-Optimal Reinforcement Learning in Polynomial Time
We present new algorithms for reinforcement learning, and prove that they have polynomial bounds on the resources required to achieve near-optimal return in general Markov decisio...
Michael J. Kearns, Satinder P. Singh