A comparative study of reinforcement learning techniques on dialogue management

Authors:
Alexandros Papangelis
Affiliations:
Institute of Informatics & Telecommunications and Univ. of Texas at Arlington
Venue:
EACL '12 Proceedings of the Student Research Workshop at the 13th Conference of the European Chapter of the Association for Computational Linguistics
Year:
2012

Citing 17
Cited 3

Incremental multi-step Q-learning

Machine Learning - Special issue on reinforcement learning
Introduction to Reinforcement Learning

Introduction to Reinforcement Learning
On Actor-Critic Algorithms

SIAM Journal on Control and Optimization
Dynamic Programming and Optimal Control, Vol. II

Dynamic Programming and Optimal Control, Vol. II
Least-Squares SARSA(Lambda) Algorithms for Reinforcement Learning

ICNC '08 Proceedings of the 2008 Fourth International Conference on Natural Computation - Volume 02
The RavenClaw dialog management framework: Architecture and systems

Computer Speech and Language
Natural language generation as planning under uncertainty for spoken dialogue systems

EACL '09 Proceedings of the 12th Conference of the European Chapter of the Association for Computational Linguistics
The Hidden Information State model: A practical framework for POMDP-based spoken dialogue management

Computer Speech and Language
Evaluation of a hierarchical reinforcement learning spoken dialogue system

Computer Speech and Language
Online planning algorithms for POMDPs

Journal of Artificial Intelligence Research
Covariant policy search

IJCAI'03 Proceedings of the 18th international joint conference on Artificial intelligence
A two-tier user simulation model for reinforcement learning of adaptive referring expression generation policies

SIGDIAL '09 Proceedings of the SIGDIAL 2009 Conference: The 10th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Algorithms for Reinforcement Learning

Algorithms for Reinforcement Learning
An embodied dialogue system with personality and emotions

CDS '10 Proceedings of the 2010 Workshop on Companionable Dialogue Systems
Gaussian processes for fast policy optimisation of POMDP-based dialogue managers

SIGDIAL '10 Proceedings of the 11th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Kalman temporal differences

Journal of Artificial Intelligence Research
Natural actor-critic

ECML'05 Proceedings of the 16th European conference on Machine Learning

Towards adaptive dialogue systems for assistive living environments

Proceedings of the companion publication of the 2013 international conference on Intelligent user interfaces companion
An adaptive dialogue system for assessing post traumatic stress disorder

Proceedings of the 6th International Conference on PErvasive Technologies Related to Assistive Environments
An assistive object manipulation system

Proceedings of the 6th International Conference on PErvasive Technologies Related to Assistive Environments

Quantified Score

Hi-index	0.00

Visualization

Abstract

Adaptive Dialogue Systems are rapidly becoming part of our everyday lives. As they progress and adopt new technologies they become more intelligent and able to adapt better and faster to their environment. Research in this field is currently focused on how to achieve adaptation, and particularly on applying Reinforcement Learning (RL) techniques, so a comparative study of the related methods, such as this, is necessary. In this work we compare several standard and state of the art online RL algorithms that are used to train the dialogue manager in a dynamic environment, aiming to aid researchers/developers choose the appropriate RL algorithm for their system. This is the first work, to the best of our knowledge, to evaluate online RL algorithms on the dialogue problem and in a dynamic environment.