Fetching the paper…

Reading the bibliography…

2016

SimpleDS: A Simple Deep Reinforcement Learning Dialogue System

Cuayáhuitl, Heriberto

Original
PDF
Post on X

Understand

This paper presents 'SimpleDS', a simple and publicly available dialogue system trained with deep reinforcement learning.

In contrast to previous reinforcement learning dialogue systems, this system avoids manual feature engineering by performing action selection directly from raw text of the last system and (noisy) user responses.
Our initial results, in the restaurant domain, show that it is indeed possible to induce reasonable dialogue behaviour with an approach that aims for high levels of automation in dialogue control for intelligent interactive agents.

SimpleDS: A Simple Deep Reinforcement Learning Dialogue System · Around

Built on

Automating spoken dialogue management design using machine learning: An industry perspective
Paek, T., Pieraccini, R.: · 2008
Earlier work this paper cites.
Algorithms for Reinforcement Learning
Szepesvári, C.: · 2010
Earlier work this paper cites.
Rectified linear units improve restricted boltzmann machines
Nair, V., Hinton, G.E.: · 2010
Earlier work this paper cites.
Evaluation of a hierarchical reinforcement learning spoken dialogue system
Cuayáhuitl, H., Renals, S., Lemon, O., Shimodaira, H.: · 2010
Earlier work this paper cites.

Similar

Spatially-aware dialogue control using hierarchical reinforcement learning
Cuayáhuitl, H., Dethlefs, N.: · 2011
Cited alongside, same era.
Playing atari with deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., Riedmiller, M.: · 2013
Cited alongside, same era.
Nonstrict hierarchical reinforcement learning for interactive systems and robots
Cuayáhuitl, H., Kruijff-Korbayová, I., Dethlefs, N.: · 2014
Cited alongside, same era.

Then

Strategic dialogue management via deep reinforcement learning
Cuayáhuitl, H., Keizer, S., Lemon, O.: · 2015
Later among the works it cites.
ConvNetJS: A javascript library for training deep learning models
Karpathy, A.: · 2015
Later among the works it cites.
Convolutional, long short-term memory, fully connected deep neural networks
Original
Sainath, T.N., Vinyals, O., Senior, A.W., Sak, H.: · 2015
Later among the works it cites.

Beyond the bibliography

alphaXiv searches the wider corpus for related work and actual follow-ups.

Open on alphaXiv

alphaXiv is searching for related work…