Reinforcement Learning Based Dialogue Management Strategy

Saha, Tulika; Gupta, Dhawal; Saha, Sriparna; Bhattacharyya, Pushpak

doi:10.1007/978-3-030-04182-3_32

Cited by 6 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There is also a variant called DDQN with Prioritized Experience Replay (DDQN-PER) where it shows significant improvement with an average dialogue length of 1342.3, -13.51 average episodic reward, and only 52.56 hours of training time. Additionally, there is also a test where DDQN-PER is not paired with any algorithms and it has maintained a good balance between performance and training time [28].…”

Section: Algorithm Suited Use Case Commonly Used In Advantagesmentioning

confidence: 99%

“…Standard Deep Q-Networks (DQN) also has showcased reasonably good performance with an average dialogue length of 673.45 and average episodic reward of -6.89. The training time needed for this variant is also relatively efficient clocking in only around 71.97 hours [28]. Nonetheless, the preferred variant can depend on the project scope and problems statements given.…”

Section: Algorithm Suited Use Case Commonly Used In Advantagesmentioning

confidence: 99%

See 1 more Smart Citation

A Systematic Literature Review: A Comparison Of Available Approaches In Chatbot And Dialogue Manager Development

Jayavardhana,

Sanjaya

2023

International Journal of Science, Technology & Management

View full text Add to dashboard Cite

The present study reviewed a number of articles chosen from a screening and selecting process on the various different methods that can be used in the context of chatbot development and dialogue managers. Since chatbots have seen a significant rise in popularity and have played an important role in helping humans complete daily tasks, this systematic literature review (SLR) aims to act as a guidance for future research. During the process of analyzing and extracting data from the 13 articles chosen, it has been identified that Artificial Neural Network (ANN), Ensemble Learning, Recurrent Neural Network (RNN), and Long-Short Term Memory (LSTM) is among some of the most popular algorithms used for developing a chatbot. Where all of these algorithms are suitable for each unique use case where it offers different advantages when implemented. Other than that, dialogue managers lean more towards the field of Deep Reinforcement Learning (DRL), where Deep Q-Networks (DQN) and its variants such as Double Deep-Q Networks (DDQN) and DDQN with Personalized Experience Replay (DDQN-PER) is commonly used. All these variants have different averages on episodic reward and dialogue length, along with different training time needed which indicates the computational power needed. This SLR aims to identify the methods that can be used and identify the best proven method to be applied in future research.

show abstract

Section: Algorithm Suited Use Case Commonly Used In Advantagesmentioning

confidence: 99%

Section: Algorithm Suited Use Case Commonly Used In Advantagesmentioning

confidence: 99%