Sciweavers

1236 search results - page 74 / 248
» Opposition-Based Reinforcement Learning
Sort
View
ICCBR
2005
Springer
15 years 6 months ago
CBR for State Value Function Approximation in Reinforcement Learning
CBR is one of the techniques that can be applied to the task of approximating a function over high-dimensional, continuous spaces. In Reinforcement Learning systems a learning agen...
Thomas Gabel, Martin A. Riedmiller
120
Voted
ACL
2010
14 years 10 months ago
Learning to Adapt to Unknown Users: Referring Expression Generation in Spoken Dialogue Systems
We present a data-driven approach to learn user-adaptive referring expression generation (REG) policies for spoken dialogue systems. Referring expressions can be difficult to unde...
Srinivasan Janarthanam, Oliver Lemon
77
Voted
PDPTA
2003
15 years 2 months ago
Java Resources for Teaching Reinforcement Learning
— In this paper we present a library of classes for programming reinforcement learning simulations in Java. This library is based upon the standard by Sutton and Santamaria [1], ...
Amy J. Kerr, Todd W. Neller, Christopher J. La Pil...
117
Voted
AROBOTS
2008
131views more  AROBOTS 2008»
15 years 7 days ago
Active audition using the parameter-less self-organising map
This paper presents a novel method for enabling a robot to determine the position of a sound source in three dimensions using just two microphones and interaction with its environm...
Erik Berglund, Joaquin Sitte, Gordon Wyeth
123
Voted
AGI
2011
14 years 4 months ago
Measuring Agent Intelligence via Hierarchies of Environments
Under Legg’s and Hutter’s formal measure [1], performance in easy environments counts more toward an agent’s intelligence than does performance in difficult environments. An ...
Bill Hibbard