46 search results - page 2 / 10 » A Sparse Sampling Algorithm for Near-Optimal Planning in Lar... |
ICML
2006
IEEE
14 years 5 months ago
2006
IEEE
Recent decision-theoric planning algorithms are able to find optimal solutions in large problems, using Factored Markov Decision Processes (fmdps). However, these algorithms need ...
ICML
2006
IEEE
14 years 5 months ago
2006
IEEE
For a Markov Decision Process with finite state (size S) and action spaces (size A per state), we propose a new algorithm--Delayed Q-Learning. We prove it is PAC, achieving near o...
UAI
2003
13 years 6 months ago
2003
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...
ICRA
2007
IEEE
13 years 11 months ago
2007
IEEE
— We introduce the Oracular Partially Observable Markov Decision Process (OPOMDP), a type of POMDP in which the world produces no observations; instead there is an “oracle,” ...
AAAI
1997
13 years 6 months ago
1997
Many stochastic planning problems can be represented using Markov Decision Processes (MDPs). A difficulty with using these MDP representations is that the common algorithms for so...