DMCA
Inverse Reinforcement Learning for Micro-Turn Management
| Citations: | 3 - 0 self |
BibTeX
@MISC{Kim_inversereinforcement,
author = {Dongho Kim and Catherine Breslin and Pirros Tsiakoulis and Matthew Henderson and Steve Young},
title = {Inverse Reinforcement Learning for Micro-Turn Management},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Existing spoken dialogue systems are typically not de-signed to provide natural interaction since they impose a strict turn-taking regime in which a dialogue consists of interleaved system and user turns. To allow more responsive and natural interaction, this paper describes a system in which turn-taking decisions are taken at a more fine-grained micro-turn level. A decision-theoretic approach is then applied to optimise turn-taking control. Inverse reinforcement learning is used to cap-ture the complex but natural behaviours from human-human di-alogues and optimise interaction without specifying a reward function manually. Using a corpus of human-human interac-tion, experiments show that IRL is able to learn an effective reward function which outperforms a comparable handcrafted policy. Index Terms: dialogue management, spoken dialogue systems, inverse reinforcement learning, Markov decision processes
Keyphrases
inverse reinforcement learning micro-turn management natural interaction spoken dialogue system index term strict turn-taking regime user turn effective reward function dialogue management natural behaviour turn-taking decision reward function interleaved system decision-theoretic approach turn-taking control human-human interac-tion human-human di-alogues fine-grained micro-turn level markov decision process comparable handcrafted policy
