Skip to Main content Skip to Navigation
Conference papers

Reward Shaping for Statistical Optimisation of Dialogue Management

Abstract : This paper investigates the impact of reward shaping on a reinforcement learning-based spoken dialogue system's learning. A diffuse reward function gives a reward after each transition between two dialogue states. A sparse function only gives a reward at the end of the dialogue. Reward shaping consists of learning a diffuse function without modifying the optimal policy compared to a sparse one. Two reward shaping methods are applied to a corpus of dialogues evaluated with numerical performance scores. Learning with these functions is compared to the sparse case and it is shown, on simulated dialogues, that the policies learnt after reward shaping lead to higher performance.
Document type :
Conference papers
Complete list of metadata
Contributor : Sébastien van Luchene Connect in order to contact the contributor
Submitted on : Friday, October 4, 2013 - 10:57:42 AM
Last modification on : Tuesday, December 15, 2020 - 3:56:43 AM

Links full text




Layla El Asri, Romain Laroche, Olivier Pietquin. Reward Shaping for Statistical Optimisation of Dialogue Management. SLSP 2013, Jul 2013, Tarragona, Spain. pp.93-101, ⟨10.1007/978-3-642-39593-2_8⟩. ⟨hal-00869809⟩



Les métriques sont temporairement indisponibles