Learning dialogue strategies within the Markov decision process framework

By Esther Levin, Roberto Pieraccini, W. Eckert. 1997

Subfields: Reinforcement Learning, Dialogue & Conversational AI

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Reinforcement Learning

In Dialogue & Conversational AI

Citations in the corpus

Deep Reinforcement Learning for Dialogue Generation (2016, methodology): “Efforts include statistical models such as Markov Decision Processes (MDPs) (Levin et al., 1997; Levin et al., 2000; Walker et al., 2003; Pieraccini et al., 2009), POMDP (Young et al.”
A Survey of Available Corpora For Building Data-Driven Dialogue Systems: The Journal Version (2015, methodology): “…training dialogue systems online through live interaction with humans, and offline using user simulator models and reinforcement learning methods (Levin et al., 1997; Georgila et al., 2006; Paek, 2006; Schatzmann et al., 2007; Jung et al., 2009; Schatzmann and Young, 2009; Gašić et al., 2010,…”
Dialogue Learning With Human-In-The-Loop (2016, neutral): “Efforts include Markov Decision Processes (MDPs) (Levin et al., 1997; 2000; Walker et al., 2003; Pierac-cini et al., 2009), POMDP models (Young et al., 2010; 2013; Gaˇsic et al., 2013; 2014) and policy learning (Su et al., 2016).”
Policy Networks with Two-Stage Training for Dialogue Systems (2016, methodology): “The statistical optimization of dialogue management in dialogue systems through Reinforcement Learning (RL) has been an active thread of research for more than two decades (Levin et al., 1997; Lemon and Pietquin, 2007; Laroche et al., 2010; Gaˇsi´c et al., 2012; Daubigney et al., 2012).”
BBQ-Networks: Efficient Exploration in Deep Reinforcement Learning for Task-Oriented Dialogue Systems (2016, background): “The conversation process above can be naturally mapped to the reinforcement learning (RL) framework, as follows (Levin, Pieraccini, and Eckert 1997).”
Strategy and Policy Learning for Non-Task-Oriented Conversational Systems (2016, background): “Researchers have proposed to design dialogue systems in the formalism of Markov decision processes (MDPs) (Levin et al., 1997) or partially observable Markov decision processes (POMDPs) (Williams and Young, 2007).”
End-to-end optimization of goal-driven and visually grounded dialogue systems (2017, methodology): “As a consequence, reinforcement learning has been applied to dialogue systems since the late 90s [Levin et al., 1997; Singh et al., 1999] and dialogue optimization has been generally more studied than dialogue generation.”
Submission Category : Applications , Preference : ORAL Reinforcement Learning for Spoken Dialogue Systems (2007, unknown): “Recently, a number of authors have proposed treating dialog ue design in the formalism of Markov decision processes (MDPs)[1, 3, 6].”
Efﬁcient Exploration for Dialogue Policy Learning with BBQ Networks & Replay Buffer Spiking (2016, methodology): “This paper also builds on prior work in task-oriented dialogue systems [Williams and Young, 2004, Gaši´c et al., 2010] and RL for learning dialogue policies [Levin et al., 1997, Singh et al., 2000, Gaši´c et al., 2010, Fatemi et al., 2016].”
Personalizing a Dialogue System With Transfer Reinforcement Learning (2016, background): “Dialogue systems can be classiﬁed into two classes: open domain dialogue systems [15, 5, 18, 12, 13] and task-oriented dialogue systems [11, 27, 24, 25, 26].”
Efficient Exploration for Dialog Policy Learning with Deep BBQ Networks \& Replay Buffer Spiking (2016, methodology): “Thus reinforcement learning (RL), in which policies are learned through interaction with an unknown environment, has emerged as a popular alternative [Levin et al., 1997, Walker, 2000, Lemon and Pietquin, 2007, Gaˇsi´c et al., 2010].”
POMDP-Based Statistical Spoken Dialog Systems: A Review (2013, methodology): “The weights can be inferred from the annotated corpus using regression, and this regression can then be used as the reward function in reinforcement learning [129], [130].”
Dynamic Planning in Open-Ended Dialogue using Reinforcement Learning (2022, methodology): “This puts us in the realm of non-standard MDPs with stochastic action sets [3].”