Matches in SemOpenAlex for { <https://semopenalex.org/work/W2966730259> ?p ?o ?g. }
Showing items 1 to 89 of
89
with 100 items per page.
- W2966730259 abstract "This paper tackles the problem of learning a questioner in the goal-oriented visual dialog task. Several previous works adopt model-free reinforcement learning. Most pretrain the model from a finite set of human-generated data. We argue that using limited demonstrations to kick-start the questioner is insufficient due to the large policy search space. Inspired by a recently proposed information theoretic approach, we develop two analytic experts to serve as a source of high-quality demonstrations for imitation learning. We then take advantage of reinforcement learning to refine the model towards the goal-oriented objective. Experimental results on the GuessWhat?! dataset show that our method has the combined merits of imitation and reinforcement learning, achieving the state-of-the-art performance." @default.
- W2966730259 created "2019-08-13" @default.
- W2966730259 creator A5071531458 @default.
- W2966730259 creator A5072864170 @default.
- W2966730259 date "2019-07-01" @default.
- W2966730259 modified "2023-09-24" @default.
- W2966730259 title "Learning Goal-Oriented Visual Dialog Agents: Imitating and Surpassing Analytic Experts" @default.
- W2966730259 cites W1933349210 @default.
- W2966730259 cites W2151210636 @default.
- W2966730259 cites W2558809543 @default.
- W2966730259 cites W2599940792 @default.
- W2966730259 cites W2603266952 @default.
- W2966730259 cites W2768661419 @default.
- W2966730259 cites W2892347792 @default.
- W2966730259 cites W2962957031 @default.
- W2966730259 cites W2963010567 @default.
- W2966730259 cites W2964070888 @default.
- W2966730259 doi "https://doi.org/10.1109/icme.2019.00096" @default.
- W2966730259 hasPublicationYear "2019" @default.
- W2966730259 type Work @default.
- W2966730259 sameAs 2966730259 @default.
- W2966730259 citedByCount "2" @default.
- W2966730259 countsByYear W29667302592021 @default.
- W2966730259 crossrefType "proceedings-article" @default.
- W2966730259 hasAuthorship W2966730259A5071531458 @default.
- W2966730259 hasAuthorship W2966730259A5072864170 @default.
- W2966730259 hasBestOaLocation W29667302592 @default.
- W2966730259 hasConcept C107457646 @default.
- W2966730259 hasConcept C111919701 @default.
- W2966730259 hasConcept C119857082 @default.
- W2966730259 hasConcept C126388530 @default.
- W2966730259 hasConcept C127413603 @default.
- W2966730259 hasConcept C136764020 @default.
- W2966730259 hasConcept C154945302 @default.
- W2966730259 hasConcept C15744967 @default.
- W2966730259 hasConcept C173853756 @default.
- W2966730259 hasConcept C177264268 @default.
- W2966730259 hasConcept C199360897 @default.
- W2966730259 hasConcept C201995342 @default.
- W2966730259 hasConcept C2778572836 @default.
- W2966730259 hasConcept C2780451532 @default.
- W2966730259 hasConcept C41008148 @default.
- W2966730259 hasConcept C77805123 @default.
- W2966730259 hasConcept C97541855 @default.
- W2966730259 hasConceptScore W2966730259C107457646 @default.
- W2966730259 hasConceptScore W2966730259C111919701 @default.
- W2966730259 hasConceptScore W2966730259C119857082 @default.
- W2966730259 hasConceptScore W2966730259C126388530 @default.
- W2966730259 hasConceptScore W2966730259C127413603 @default.
- W2966730259 hasConceptScore W2966730259C136764020 @default.
- W2966730259 hasConceptScore W2966730259C154945302 @default.
- W2966730259 hasConceptScore W2966730259C15744967 @default.
- W2966730259 hasConceptScore W2966730259C173853756 @default.
- W2966730259 hasConceptScore W2966730259C177264268 @default.
- W2966730259 hasConceptScore W2966730259C199360897 @default.
- W2966730259 hasConceptScore W2966730259C201995342 @default.
- W2966730259 hasConceptScore W2966730259C2778572836 @default.
- W2966730259 hasConceptScore W2966730259C2780451532 @default.
- W2966730259 hasConceptScore W2966730259C41008148 @default.
- W2966730259 hasConceptScore W2966730259C77805123 @default.
- W2966730259 hasConceptScore W2966730259C97541855 @default.
- W2966730259 hasLocation W29667302591 @default.
- W2966730259 hasLocation W29667302592 @default.
- W2966730259 hasOpenAccess W2966730259 @default.
- W2966730259 hasPrimaryLocation W29667302591 @default.
- W2966730259 hasRelatedWork W1584210162 @default.
- W2966730259 hasRelatedWork W2112458651 @default.
- W2966730259 hasRelatedWork W2161903956 @default.
- W2966730259 hasRelatedWork W2604382266 @default.
- W2966730259 hasRelatedWork W2618170641 @default.
- W2966730259 hasRelatedWork W2794908222 @default.
- W2966730259 hasRelatedWork W2795910581 @default.
- W2966730259 hasRelatedWork W2960390321 @default.
- W2966730259 hasRelatedWork W2963073229 @default.
- W2966730259 hasRelatedWork W2965723696 @default.
- W2966730259 hasRelatedWork W2971118689 @default.
- W2966730259 hasRelatedWork W3015216216 @default.
- W2966730259 hasRelatedWork W3017861469 @default.
- W2966730259 hasRelatedWork W3029466658 @default.
- W2966730259 hasRelatedWork W3088855030 @default.
- W2966730259 hasRelatedWork W3116700304 @default.
- W2966730259 hasRelatedWork W3132095429 @default.
- W2966730259 hasRelatedWork W3183955832 @default.
- W2966730259 hasRelatedWork W3195099242 @default.
- W2966730259 hasRelatedWork W6705875 @default.
- W2966730259 isParatext "false" @default.
- W2966730259 isRetracted "false" @default.
- W2966730259 magId "2966730259" @default.
- W2966730259 workType "article" @default.