Sciweavers

48 search results - page 8 / 10
» Interpolant-Based Transition Relation Approximation
Sort
View
CDC
2008
IEEE
156views Control Systems» more  CDC 2008»
14 years 11 days ago
Diagnosability of hybrid automata with measurement uncertainty
— We propose a diagnosability notion that depends on two parameters denoted as (δd, δm) for the general class of transition systems where the observable output is given by disc...
Maria Domenica Di Benedetto, Stefano Di Gennaro, A...
EEF
2000
13 years 9 months ago
Distributed and Structured Analysis Approaches to Study Large and Complex Systems
Both the logic and the stochastic analysis of discrete-state systems are hindered by the combinatorial growth of the state space underlying a high-level model. In this work, we con...
Gianfranco Ciardo
ATAL
2008
Springer
13 years 8 months ago
Autonomous transfer for reinforcement learning
Recent work in transfer learning has succeeded in making reinforcement learning algorithms more efficient by incorporating knowledge from previous tasks. However, such methods typ...
Matthew E. Taylor, Gregory Kuhlmann, Peter Stone
UAI
2003
13 years 7 months ago
Learning Generative Models of Similarity Matrices
Recently, spectral clustering (a.k.a. normalized graph cut) techniques have become popular for their potential ability at finding irregularlyshaped clusters in data. The input to...
Rómer Rosales, Brendan J. Frey
PKDD
2010
Springer
179views Data Mining» more  PKDD 2010»
13 years 3 months ago
Gaussian Processes for Sample Efficient Reinforcement Learning with RMAX-Like Exploration
Abstract. We present an implementation of model-based online reinforcement learning (RL) for continuous domains with deterministic transitions that is specifically designed to achi...
Tobias Jung, Peter Stone