Sciweavers

132 search results - page 16 / 27
» Rewarding Behaviors
Sort
View
107
Voted
HRI
2009
ACM
15 years 10 months ago
Creating and using matrix representations of social interaction
This paper explores the use of an outcome matrix as a computational representation of social interaction suitable for implementation on a robot. An outcome matrix expresses the re...
Alan R. Wagner
120
Voted
TSMC
2002
98views more  TSMC 2002»
15 years 3 months ago
The STAR automaton: expediency and optimality properties
Abstract--We present the STack ARchitecture (STAR) automaton. It is a fixed structure, multiaction, reward-penalty learning automaton, characterized by a star-shaped state transiti...
Anastasios A. Economides, Athanasios Kehagias
136
Voted
JSSPP
2004
Springer
15 years 9 months ago
Are User Runtime Estimates Inherently Inaccurate?
Computer system batch schedulers typically require information from the user upon job submission, including a runtime estimate. Inaccuracy of these runtime estimates, relative to ...
Cynthia Bailey Lee, Yael Schwartzman, Jennifer Har...
124
Voted
AAAI
2012
13 years 6 months ago
An Intelligent Battery Controller Using Bias-Corrected Q-learning
The transition to renewables requires storage to help smooth short-term variations in energy from wind and solar sources, as well as to respond to spikes in electricity spot price...
Donghun Lee, Warren B. Powell
118
Voted
ATAL
2004
Springer
15 years 9 months ago
Fitting and Compilation of Multiagent Models through Piecewise Linear Functions
Decision-theoretic models have become increasingly popular as a basis for solving agent and multiagent problems, due to their ability to quantify the complex uncertainty and prefe...
David V. Pynadath, Stacy Marsella