Access the full text.
Sign up today, get DeepDyve free for 14 days.
S. Clark, J. Hockenmaier, Mark Steedman (2002)
Building Deep Dependency Structures using a Wide-Coverage CCG Parser
Kai-Florian Richter, M. Duckham (2008)
Simplest Instructions: Finding Easy-to-Describe Routes for Navigation
A. Klippel, T. Tenbrink, D. Montello, M. Dimitrova-Vulchanova (2012)
The Role of Structure and Function in the Conceptualization of Directions
Nina Dethlefs, H. Cuayáhuitl (2010)
Hierarchical Reinforcement Learning for Adaptive Text Generation
(2003)
Artificial Intelligence: A Modern Approach
Nina Dethlefs, Heriberto Cuay, Kai-Florian Richter, E. Andonova, J. Bateman (2010)
Evaluating Task Success in a Dialogue System for Indoor Navigation
A. Belz (2008)
Automatic generation of weather forecast texts using comprehensive probabilistic generation-space modelsNatural Language Engineering, 14
(2007)
Non-localized, interactive multimodal direction giving
Oliver Lemon, Kallirroi Georgila, James Henderson (2006)
EVALUATING EFFECTIVENESS AND PORTABILITY OF REINFORCEMENT LEARNED DIALOGUE STRATEGIES WITH REAL USERS: THE TALK TOWNINFO EVALUATION2006 IEEE Spoken Language Technology Workshop
M. Denis (1997)
The description of routes : A cognitive approach to the production of spatial discourse, 16
R. Stiefelhagen, H. Ekenel, C. Fügen, Petra Gieselmann, H. Holzapfel, Florian Kraft, Kai Nickel, M. Voit, A. Waibel (2007)
Enabling Multimodal Human–Robot Interaction for the Karlsruhe Humanoid RobotIEEE Transactions on Robotics, 23
S. Young, Milica Gasic, Simon Keizer, François Mairesse, J. Schatzmann, Blaise Thomson, Kai Yu (2010)
The Hidden Information State model: A practical framework for POMDP-based spoken dialogue managementComput. Speech Lang., 24
Thomas Dietterich (1999)
Hierarchical Reinforcement Learning with the MAXQ Value Function DecompositionArXiv, cs.LG/9905014
H. Cuayáhuitl, S. Renals, Oliver Lemon, H. Shimodaira (2010)
Evaluation of a hierarchical reinforcement learning spoken dialogue systemComput. Speech Lang., 24
A. Klippel, Stefan Hansen, Kai-Florian Richter, S. Winter (2009)
Urban granularities—a data structure for cognitively ergonomic route directionsGeoInformatica, 13
Jason Williams (2006)
Partially Observable Markov Decision Processes for Spoken Dialogue Management
T. Becker, Claus Nagel, T. Kolbe (2009)
A Multilayered Space-Event Model for Navigation in Indoor Spaces
Thomas Prommer, H. Holzapfel, A. Waibel (2006)
Rapid simulation-driven reinforcement learning of multimodal dialog strategies in human-robot interaction
Blaise Thomson (2013)
Statistical methods for spoken dialogue management
James Henderson, Oliver Lemon, Kallirroi Georgila (2008)
Hybrid Reinforcement/Supervised Learning of Dialogue Policies from Fixed Data SetsComputational Linguistics, 34
Thomas Dietterich (2000)
An Overview of MAXQ Hierarchical Reinforcement Learning
J. Bateman (1997)
Enabling technology for multilingual natural language generation: the KPML development environmentNatural Language Engineering, 3
H. Hochmair (2008)
PDA-Assisted Indoor-Navigation with Imprecise Positioning: Results of a Desktop Usability Study
S. Werner, B. Krieg-Brückner, T. Herrmann (2000)
Modelling Navigational Knowledge by Route Graphs
F. Fernández, M. Veloso (2006)
Probabilistic policy reuse in a reinforcement learning agent
H. Cuayáhuitl, Nina Dethlefs, Kai-Florian Richter, T. Tenbrink, J. Bateman (2010)
A Dialogue System for Indoor Wayfinding Using Text-Based Natural LanguageInt. J. Comput. Linguistics Appl., 1
M. Duckham, L. Kulik (2003)
"Simplest" Paths: Automated Route Selection for Navigation
H. Cuayáhuitl, S. Renals, Oliver Lemon, H. Shimodaira (2007)
Hierarchical dialogue optimization using semi-Markov decision processes
Verena Rieser, Oliver Lemon (2008)
Learning Effective Multimodal Dialogue Strategies from Wizard-of-Oz Data: Bootstrapping and Evaluation
(2011)
ACM Transactions on Speech and Language Processing
(2007)
Providing individual route instructions for indoor wayfinding in complex, multi-level buildings
E. Levin, R. Pieraccini, W. Eckert (2000)
A stochastic model of human-machine interaction for learning dialog strategiesIEEE Trans. Speech Audio Process., 8
Oliver Lemon, Anne Bracy, A. Gruenstein, S. Peters (2001)
The WITAS multi-modal dialogue system I
J. Wyatt (2005)
Planning clarification questions to resolve ambiguous references to objects
H. Cuayáhuitl (2009)
Hierarchical Reinforcement Learning for Spoken Dialogue Systems
C. Kray, Gerd Kortuem, A. Krüger (2005)
Adaptive navigation support with public displaysProceedings of the 10th international conference on Intelligent user interfaces
O. Pietquin (2004)
A Framework for Unsupervised Learning of Dialogue Strategies
Oliver Lemon (2011)
Learning what to say and how to say it: Joint optimisation of spoken dialogue management and natural language generationComput. Speech Lang., 25
L. Kaelbling, M. Littman, A. Moore (1996)
Reinforcement Learning: A SurveyJ. Artif. Intell. Res., 4
Dethlefs
Michael Kearns, D. Litman, Satinder Singh, M. Walker (2011)
Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun SystemJ. Artif. Intell. Res., 16
T. Tenbrink, S. Winter (2009)
Variable Granularity in Route DirectionsSpatial Cognition & Computation, 9
G. Kruijff, H. Zender, P. Jensfelt, H. Christensen (2007)
Situated Dialogue and Spatial Organization: What, Where… and Why?International Journal of Advanced Robotic Systems, 4
Molly Sorrows, S. Hirtle (1999)
The Nature of Landmarks for Real and Electronic Spaces
Hans Ohlbach, Edgar-Philipp Stoffel (2008)
Versatile Route Descriptions for Pedestrian Guidance in Buildings - Conceptual Model and Systematic Method
M. Raubal, S. Winter (2002)
Enriching Wayfinding Instructions with Local Landmarks
S. Janarthanam, Oliver Lemon (2010)
Learning to Adapt to Unknown Users: Referring Expression Generation in Spoken Dialogue Systems
Matthias Denecke, Kohji Dohsaka, Mikio Nakano (2004)
Fast Reinforcement Learning of Dialogue Policies Using Stable Function Approximation
(2001)
Supporting the Navigation Task: Characteristics of 'G'ood Landmarks
R. Ross, J. Bateman (2009)
Daisie: Information State Dialogues for Situated Systems
Joelle Pineau, Geoffrey Gordon, S. Thrun (2004)
Tractable planning under uncertainty: exploiting structure
M. Walker, C. Kamm, D. Litman (2000)
Towards developing general models of usability with PARADISENatural Language Engineering, 6
S. Young (2000)
Probabilistic methods in spoken–dialogue systemsPhilosophical Transactions of the Royal Society of London. Series A: Mathematical, Physical and Engineering Sciences, 358
H. Cuayáhuitl, Nina Dethlefs, L. Frommberger, Kai-Florian Richter, J. Bateman (2010)
Generating Adaptive Route Instructions Using Hierarchical Reinforcement Learning
M. Walker (2000)
An Application of Reinforcement Learning to Dialogue Strategy Selection in a Spoken Dialogue System for EmailJ. Artif. Intell. Res., 12
K. Dautenhahn (2008)
Special Issue on “Human and Robot Interactive Communication”Interaction Studies, 9
Dave Toney (2007)
Evolutionary reinforcement learning of spoken dialogue strategies
Kristin Lovelace, M. Hegarty, D. Montello (1999)
Elements of Good Route Directions in Familiar and Unfamiliar Environments
Richard Sutton, A. Barto (1998)
Introduction to Reinforcement Learning
A. May, T. Ross, S. Bayer (2003)
Drivers' Information Requirements when Navigating in an Urban EnvironmentJournal of Navigation, 56
J. Schatzmann, K. Weilhammer, Matthew Stuttle, Steve Young (2006)
A survey of statistical user simulation techniques for reinforcement-learning of dialogue management strategiesThe Knowledge Engineering Review, 21
Spatially-Aware Dialogue Control Using Hierarchical Reinforcement Learning HERIBERTO CUAYAHUITL and NINA DETHLEFS, University of Bremen This article addresses the problem of scalable optimization for spatially-aware dialogue systems. These kinds of systems must perceive, reason, and act about the spatial environment where they are embedded. We formulate the problem in terms of Semi-Markov Decision Processes and propose a hierarchical reinforcement learning approach to optimize subbehaviors rather than full behaviors. Because of the vast number of policies that are required to control the interaction in a dynamic environment (e.g., a dialogue system assisting a user to navigate in a building from one location to another), our learning approach is based on two stages: (a) the rst stage learns low-level behavior, in advance; and (b) the second stage learns high-level behavior, in real time. For such a purpose we extend an existing algorithm in the literature of reinforcement learning in order to support reusable policies and therefore to perform fast learning. We argue that our learning approach makes the problem feasible, and we report on a novel reinforcement learning dialogue system that performs a joint optimization between dialogue and spatial behaviors. Our experiments, using simulated and real environments, are based on
ACM Transactions on Speech and Language Processing (TSLP) – Association for Computing Machinery
Published: May 1, 2011
Read and print from thousands of top scholarly journals.
Already have an account? Log in
Bookmark this article. You can see your Bookmarks on your DeepDyve Library.
To save an article, log in first, or sign up for a DeepDyve account if you don’t already have one.
Copy and paste the desired citation format or use the link below to download a file formatted for EndNote
Access the full text.
Sign up today, get DeepDyve free for 14 days.
All DeepDyve websites use cookies to improve your online experience. They were placed on your computer when you launched this website. You can change your cookie settings through your browser.