Sciweavers

32 search results - page 5 / 7
» Regression with Respect to Sensing Actions and Partial State...
Sort
View
EUROCAST
2007
Springer
182views Hardware» more  EUROCAST 2007»
14 years 1 months ago
A k-NN Based Perception Scheme for Reinforcement Learning
Abstract a paradigm of modern Machine Learning (ML) which uses rewards and punishments to guide the learning process. One of the central ideas of RL is learning by “direct-online...
José Antonio Martin H., Javier de Lope Asia...
GECCO
1999
Springer
133views Optimization» more  GECCO 1999»
13 years 11 months ago
Evolution of Goal-Directed Behavior from Limited Information in a Complex Environment
In this paper, we apply an evolutionary algorithm to learning behavior on a novel, interesting task to explore the general issue of learning e ective behaviors in a complex enviro...
Matthew R. Glickman, Katia P. Sycara
ESAW
2007
Springer
13 years 9 months ago
Progress Appraisal as a Challenging Element of Coordination in Human and Machine Joint Activity
Joint activity, as we define it, is a mutually interdependent social endeavor that requires sufficient predictability among participating parties to enable coordination. Coordinati...
Paul J. Feltovich, Jeffrey M. Bradshaw, William J....
ICRA
2010
IEEE
163views Robotics» more  ICRA 2010»
13 years 5 months ago
Exploiting domain knowledge in planning for uncertain robot systems modeled as POMDPs
Abstract— We propose a planning algorithm that allows usersupplied domain knowledge to be exploited in the synthesis of information feedback policies for systems modeled as parti...
Salvatore Candido, James C. Davidson, Seth Hutchin...
POPL
2012
ACM
12 years 2 months ago
Access permission contracts for scripting languages
The ideal software contract fully specifies the behavior of an operation. Often, in particular in the context of scripting languages, a full specification may be cumbersome to s...
Phillip Heidegger, Annette Bieniusa, Peter Thieman...