Sciweavers

291 search results - page 8 / 59
» Implementation with a bounded action space
Sort
View
TABLETOP
2008
IEEE
14 years 3 months ago
Presenting using two-handed interaction in open space
Based on recent demonstrations of low-cost, infrared-based point tracking, we explore two-handed, surface-less interaction for presentation. On both hands, thumb and index finger...
Luc Vlaming, Jasper Smit, Tobias Isenberg
IJRR
2011
174views more  IJRR 2011»
13 years 3 months ago
Bounding on rough terrain with the LittleDog robot
— In this paper we develop an RRT-based motion planner that achieved bounding in simulation with the LittleDog robot over extremely rough terrain. LittleDog is a quadruped robot ...
Alexander C. Shkolnik, Michael Levashov, Ian R. Ma...
EC
2010
127views ECommerce» more  EC 2010»
13 years 6 months ago
Representation Invariant Genetic Operators
A genetic algorithm is invariant with respect to a set of representations if it runs the same no matter which of the representations is used. We formalize this concept mathematica...
Jonathan E. Rowe, Michael D. Vose, Alden H. Wright
EWRL
2008
13 years 10 months ago
Efficient Reinforcement Learning in Parameterized Models: Discrete Parameter Case
We consider reinforcement learning in the parameterized setup, where the model is known to belong to a parameterized family of Markov Decision Processes (MDPs). We further impose ...
Kirill Dyagilev, Shie Mannor, Nahum Shimkin
ATAL
2005
Springer
14 years 2 months ago
Law-governed Linda as a semantics for agent dialogue protocols
Tuple spaces and the associated Linda language are a popular model for distributed computation, and Law-Governed Linda (LGL) is a variant allowing processes to have differential ...
Sylvie Doutre, Peter McBurney, Michael Wooldridge