Sciweavers

287 search results - page 43 / 58
» Communication complexity as a lower bound for learning in ga...
Sort
View
ALT
1999
Springer
14 years 27 days ago
PAC Learning with Nasty Noise
We introduce a new model for learning in the presence of noise, which we call the Nasty Noise model. This model generalizes previously considered models of learning with noise. Th...
Nader H. Bshouty, Nadav Eiron, Eyal Kushilevitz
LFCS
2007
Springer
14 years 2 months ago
Model Checking Knowledge and Linear Time: PSPACE Cases
We present a general algorithm scheme for model checking logics of knowledge, common knowledge and linear time, based on simulations to a class of structures that capture the way t...
Kai Engelhardt, Peter Gammie, Ron van der Meyden
ATAL
2007
Springer
14 years 2 months ago
Advice taking in multiagent reinforcement learning
This paper proposes the β-WoLF algorithm for multiagent reinforcement learning (MARL) in the stochastic games framework that uses an additional “advice” signal to inform agen...
Michael Rovatsos, Alexandros Belesiotis
JALC
2007
90views more  JALC 2007»
13 years 8 months ago
Learning Unary Automata
We determine the complexity of learning problems for unary regular languages. We begin by investigating the minimum consistent dfa (resp. nfa) problem which is known not to be app...
Gregor Gramlich, Ralf Herrmann
STOC
2006
ACM
121views Algorithms» more  STOC 2006»
14 years 9 months ago
Narrow proofs may be spacious: separating space and width in resolution
The width of a resolution proof is the maximal number of literals in any clause of the proof. The space of a proof is the maximal number of clauses kept in memory simultaneously if...
Jakob Nordström