Learning automata-based approach to learn dialogue policies in large state space. (1st January 2012)

• Record Type: Journal Article
• Authors: Kumaravelan, G.; Sivakumar, R.
• Is Part Of: International journal of intelligent information and database systems. Volume 6:Number 2(2012)
• Page Start: 180
• Page End: 199
• Publication Date: 2012-01-01
• Subjects: spoken dialogue system -- SDS -- reinforcement learning -- RL -- learning automata -- LA -- Markov decision process -- MDP -- human-computer interaction; Database management -- Computer programs -- Periodicals; Information retrieval -- Computer programs -- Periodicals; Information storage and retrieval systems -- Computer programs -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Intelligent agents (Computer software) -- Periodicals; 006.33
• Languages: English
• ISSNs: 1751-5858

Abstract

This paper addresses the problem of scalable optimisation of dialogue policies in speech-based conversational systems using reinforcement learning. More specifically, for large state spaces several difficulties like large tables, an account of prior knowledge and data sparsity are faced. Hence, we present an online policy learning algorithm based on hierarchical structure learning automata using eligibility trace method to find optimal dialogue strategies that cover large state spaces. The proposed algorithm is capable of deriving an optimal policy that prescribes what action should be taken in various states of conversation so as to maximise the expected total reward to attain the goal and incorporates good exploration and exploitation in its updates to improve the naturalness of human-computer interaction. The proposed model is tested using the most sophisticated evaluation framework PARADISE for accessing the travel information system.