Sciweavers

4047 search results - page 564 / 810
» The Discrete Basis Problem
Sort
View
NIPS
2007
15 years 6 months ago
Reinforcement Learning in Continuous Action Spaces through Sequential Monte Carlo Methods
Learning in real-world domains often requires to deal with continuous state and action spaces. Although many solutions have been proposed to apply Reinforcement Learning algorithm...
Alessandro Lazaric, Marcello Restelli, Andrea Bona...
AIPS
2004
15 years 6 months ago
Plays as Effective Multiagent Plans Enabling Opponent-Adaptive Play Selection
Coordinated action for a team of robots is a challenging problem, especially in dynamic, unpredictable environments. Robot soccer is an instance of a domain where well defined goa...
Michael H. Bowling, Brett Browning, Manuela M. Vel...
140
Voted
DAGSTUHL
2004
15 years 6 months ago
Simplicity Considered Fundamental to Design for Predictability
Complexity is the core problem of contemporary information technology, as the "artificial complicatedness" of its artefacts is exploding. Intellectually easy and economic...
Wolfgang A. Halang
WICSA
2001
15 years 6 months ago
Focus: A Light-Weight, Incremental Approach to Software Architecture Recovery and Evolution
During the past decade, object-orientation (OO) has become the dominant software development methodology, accompanied by a number of modeling notations, programming languages, and...
Lei Ding, Nenad Medvidovic
UAI
2003
15 years 6 months ago
Learning Continuous Time Bayesian Networks
Continuous time Bayesian networks (CTBN) describe structured stochastic processes with finitely many states that evolve over continuous time. A CTBN is a directed (possibly cycli...
Uri Nodelman, Christian R. Shelton, Daphne Koller