Sciweavers

291 search results - page 3 / 59
» Implementation with a bounded action space
Sort
View
ICML
2005
IEEE
14 years 6 months ago
Finite time bounds for sampling based fitted value iteration
In this paper we consider sampling based fitted value iteration for discounted, large (possibly infinite) state space, finite action Markovian Decision Problems where only a gener...
Csaba Szepesvári, Rémi Munos
ATAL
2007
Springer
13 years 11 months ago
A Q-decomposition and bounded RTDP approach to resource allocation
This paper contributes to solve effectively stochastic resource allocation problems known to be NP-Complete. To address this complex resource management problem, a Qdecomposition...
Pierrick Plamondon, Brahim Chaib-draa, Abder Rezak...
LPNMR
2004
Springer
13 years 10 months ago
Planning with Sensing Actions and Incomplete Information Using Logic Programming
Abstract. We present a logic programming based conditional planner that is capable of generating both conditional and sequential conformant plans in the presence of sensing actions...
Tran Cao Son, Phan Huy Tu, Chitta Baral
ENTCS
2007
85views more  ENTCS 2007»
13 years 5 months ago
Proving Approximate Implementations for Probabilistic I/O Automata
In this paper we introduce the notion of approximate implementations for Probabilistic I/O Automata (PIOA) and develop methods for proving such relationships. We employ a task str...
Sayan Mitra, Nancy A. Lynch
BC
2010
163views more  BC 2010»
13 years 2 months ago
Action and behavior: a free-energy formulation
We have previously tried to explain perceptual inference and learning under a free-energy principle that pursues Helmholtz's agenda to understand the brain in terms of energy ...
Karl J. Friston, Jean Daunizeau, James Kilner, Ste...