Matches in SemOpenAlex for { <https://semopenalex.org/work/W4285414384> ?p ?o ?g. }
- W4285414384 endingPage "1853" @default.
- W4285414384 startingPage "1840" @default.
- W4285414384 abstract "A key aspect of social human-robot interaction is natural non-verbal communication. In this work, we train an agent with batch reinforcement learning to generate nods and smiles as backchannels in order to increase the naturalness of the interaction and to engage humans. We introduce the Sequential Random Deep Q-Network (SRDQN) method to learn a policy for backchannel generation, that explicitly maximizes user engagement. The proposed SRDQN method outperforms the existing vanilla Q-learning methods when evaluated using off-policy policy evaluation techniques. Furthermore, to verify the effectiveness of SRDQN, a human-robot experiment has been designed and conducted with an expressive 3d robot head. The experiment is based on a story-shaping game designed to create an interactive social activity with the robot. The engagement of the participants during the interaction is computed from user's social signals like backchannels, mutual gaze and adjacency pair. The subjective feedback from participants and the engagement values strongly indicate that our framework is a step forward towards the autonomous learning of a socially acceptable backchanneling behavior." @default.
- W4285414384 created "2022-07-14" @default.
- W4285414384 creator A5064993025 @default.
- W4285414384 creator A5068367152 @default.
- W4285414384 creator A5073627972 @default.
- W4285414384 creator A5074744284 @default.
- W4285414384 date "2022-10-01" @default.
- W4285414384 modified "2023-09-25" @default.
- W4285414384 title "Training Socially Engaging Robots: Modeling Backchannel Behaviors with Batch Reinforcement Learning" @default.
- W4285414384 cites W103982469 @default.
- W4285414384 cites W123085430 @default.
- W4285414384 cites W1482249289 @default.
- W4285414384 cites W1530937187 @default.
- W4285414384 cites W1646707810 @default.
- W4285414384 cites W166862392 @default.
- W4285414384 cites W1893321082 @default.
- W4285414384 cites W192920577 @default.
- W4285414384 cites W1972361065 @default.
- W4285414384 cites W1991123335 @default.
- W4285414384 cites W2001564357 @default.
- W4285414384 cites W2007208280 @default.
- W4285414384 cites W2026464238 @default.
- W4285414384 cites W2035901030 @default.
- W4285414384 cites W2042170119 @default.
- W4285414384 cites W2070029678 @default.
- W4285414384 cites W2070629246 @default.
- W4285414384 cites W2071764088 @default.
- W4285414384 cites W2078013821 @default.
- W4285414384 cites W2087762538 @default.
- W4285414384 cites W2094856020 @default.
- W4285414384 cites W2096284813 @default.
- W4285414384 cites W2097799523 @default.
- W4285414384 cites W2099019320 @default.
- W4285414384 cites W2107726111 @default.
- W4285414384 cites W2111040806 @default.
- W4285414384 cites W2118748593 @default.
- W4285414384 cites W2128291347 @default.
- W4285414384 cites W2145339207 @default.
- W4285414384 cites W2146334809 @default.
- W4285414384 cites W2147272821 @default.
- W4285414384 cites W2151161180 @default.
- W4285414384 cites W2153738822 @default.
- W4285414384 cites W2161898017 @default.
- W4285414384 cites W2161956125 @default.
- W4285414384 cites W2201912979 @default.
- W4285414384 cites W2471193380 @default.
- W4285414384 cites W2560862806 @default.
- W4285414384 cites W2562683928 @default.
- W4285414384 cites W2594693247 @default.
- W4285414384 cites W2747602812 @default.
- W4285414384 cites W2766329790 @default.
- W4285414384 cites W2766470603 @default.
- W4285414384 cites W2769428625 @default.
- W4285414384 cites W2775496038 @default.
- W4285414384 cites W2807126412 @default.
- W4285414384 cites W2886970874 @default.
- W4285414384 cites W2887260263 @default.
- W4285414384 cites W2889001427 @default.
- W4285414384 cites W2894609524 @default.
- W4285414384 cites W2901843047 @default.
- W4285414384 cites W2902884642 @default.
- W4285414384 cites W2937179707 @default.
- W4285414384 cites W2968983352 @default.
- W4285414384 cites W2972320372 @default.
- W4285414384 cites W2996516495 @default.
- W4285414384 cites W3091897465 @default.
- W4285414384 cites W3099420497 @default.
- W4285414384 cites W3100944043 @default.
- W4285414384 cites W3101568187 @default.
- W4285414384 cites W4232166125 @default.
- W4285414384 cites W4240320754 @default.
- W4285414384 cites W4246277771 @default.
- W4285414384 cites W4298229048 @default.
- W4285414384 doi "https://doi.org/10.1109/taffc.2022.3190233" @default.
- W4285414384 hasPublicationYear "2022" @default.
- W4285414384 type Work @default.
- W4285414384 citedByCount "2" @default.
- W4285414384 countsByYear W42854143842022 @default.
- W4285414384 countsByYear W42854143842023 @default.
- W4285414384 crossrefType "journal-article" @default.
- W4285414384 hasAuthorship W4285414384A5064993025 @default.
- W4285414384 hasAuthorship W4285414384A5068367152 @default.
- W4285414384 hasAuthorship W4285414384A5073627972 @default.
- W4285414384 hasAuthorship W4285414384A5074744284 @default.
- W4285414384 hasBestOaLocation W42854143842 @default.
- W4285414384 hasConcept C10090317 @default.
- W4285414384 hasConcept C107457646 @default.
- W4285414384 hasConcept C121332964 @default.
- W4285414384 hasConcept C134537474 @default.
- W4285414384 hasConcept C145460709 @default.
- W4285414384 hasConcept C154945302 @default.
- W4285414384 hasConcept C15744967 @default.
- W4285414384 hasConcept C162947575 @default.
- W4285414384 hasConcept C180747234 @default.
- W4285414384 hasConcept C188116033 @default.
- W4285414384 hasConcept C19766214 @default.
- W4285414384 hasConcept C19966478 @default.
- W4285414384 hasConcept C2779916870 @default.