Sciweavers

799 search results - page 97 / 160
» Refinement and Separation Contexts
Sort
View
IJCAI
2003
13 years 11 months ago
Multiple-Goal Reinforcement Learning with Modular Sarsa(0)
We present a new algorithm, GM-Sarsa(0), for finding approximate solutions to multiple-goal reinforcement learning problems that are modeled as composite Markov decision processe...
Nathan Sprague, Dana H. Ballard
AIPS
1996
13 years 11 months ago
Expressive Planning and Explicit Knowledge
Weare concerned with the implications and interactions of three commonexpressive extensions to classical planning: conditional plans, context-dependent actions, and nondeterminist...
Robert P. Goldman, Mark S. Boddy
ECAI
2010
Springer
13 years 11 months ago
A Motivation-Based Mechanism to Design Behaviors
In human-level simulations, like video games can be, the design of character's behaviors has an important impact on simulation realism. We propose to divide it into a reasonin...
Tony Dujardin, Jean-Christophe Routier
CPHYSICS
2008
161views more  CPHYSICS 2008»
13 years 10 months ago
Implementing peridynamics within a molecular dynamics code
Peridynamics (PD) is a continuum theory that employs a nonlocal model to describe material properties. In this context, nonlocal means that continuum points separated by a finite ...
Michael L. Parks, Richard B. Lehoucq, Steven J. Pl...
ENTCS
2006
104views more  ENTCS 2006»
13 years 10 months ago
Paradigm as Organization-Oriented Coordination Language
Global component behaviours as distinguished in Paradigm, offer the ingredients for specifying inter-component coordination in separation from and consistent with detailed compone...
Luuk Groenewegen, A. W. Stam, Pieter J. Toussaint,...