Matches in SemOpenAlex for { <https://semopenalex.org/work/W3103179916> ?p ?o ?g. }
Showing items 1 to 98 of
98
with 100 items per page.
- W3103179916 abstract "Language-guided robots must be able to both ask humans questions and understand answers. Much existing work focuses only on the latter. In this paper, we go beyond instruction following and introduce a two-agent task where one agent navigates and asks questions that a second, guiding agent answers. Inspired by theory of mind, we propose the Recursive Mental Model (RMM). The navigating agent models the guiding agent to simulate answers given candidate generated questions. The guiding agent in turn models the navigating agent to simulate navigation steps it would take to generate answers. We use the progress agents make towards the goal as a reinforcement learning reward signal to directly inform not only navigation actions, but also both question and answer generation. We demonstrate that RMM enables better generalization to novel environments. Interlocutor modelling may be a way forward for human-agent RMM where robots need to both ask and answer questions." @default.
- W3103179916 created "2020-11-23" @default.
- W3103179916 creator A5030468199 @default.
- W3103179916 creator A5041302228 @default.
- W3103179916 creator A5047233371 @default.
- W3103179916 creator A5076775408 @default.
- W3103179916 creator A5088374525 @default.
- W3103179916 date "2020-01-01" @default.
- W3103179916 modified "2023-09-24" @default.
- W3103179916 title "RMM: A Recursive Mental Model for Dialogue Navigation" @default.
- W3103179916 cites W1993979041 @default.
- W3103179916 cites W2064675550 @default.
- W3103179916 cites W2101105183 @default.
- W3103179916 cites W2118781169 @default.
- W3103179916 cites W2121863487 @default.
- W3103179916 cites W2159056499 @default.
- W3103179916 cites W2194775991 @default.
- W3103179916 cites W2220374841 @default.
- W3103179916 cites W2264742718 @default.
- W3103179916 cites W2293700449 @default.
- W3103179916 cites W2396229782 @default.
- W3103179916 cites W2558809543 @default.
- W3103179916 cites W2603266952 @default.
- W3103179916 cites W2605968924 @default.
- W3103179916 cites W2768661419 @default.
- W3103179916 cites W2772001136 @default.
- W3103179916 cites W2810840719 @default.
- W3103179916 cites W2835434549 @default.
- W3103179916 cites W2885804027 @default.
- W3103179916 cites W2950801649 @default.
- W3103179916 cites W2962744691 @default.
- W3103179916 cites W2962766710 @default.
- W3103179916 cites W2963726321 @default.
- W3103179916 cites W2964101860 @default.
- W3103179916 cites W2964121744 @default.
- W3103179916 cites W2964210218 @default.
- W3103179916 cites W2964308564 @default.
- W3103179916 cites W2964339842 @default.
- W3103179916 cites W2964935470 @default.
- W3103179916 cites W2967180672 @default.
- W3103179916 cites W2967186499 @default.
- W3103179916 cites W2970340522 @default.
- W3103179916 cites W2970972751 @default.
- W3103179916 cites W2979727876 @default.
- W3103179916 cites W2997517419 @default.
- W3103179916 cites W2998008599 @default.
- W3103179916 cites W3020712669 @default.
- W3103179916 cites W3029418112 @default.
- W3103179916 cites W3034376488 @default.
- W3103179916 cites W3034500398 @default.
- W3103179916 cites W3034533785 @default.
- W3103179916 cites W3034912332 @default.
- W3103179916 cites W3034984114 @default.
- W3103179916 cites W3106571068 @default.
- W3103179916 doi "https://doi.org/10.18653/v1/2020.findings-emnlp.157" @default.
- W3103179916 hasPublicationYear "2020" @default.
- W3103179916 type Work @default.
- W3103179916 sameAs 3103179916 @default.
- W3103179916 citedByCount "20" @default.
- W3103179916 countsByYear W31031799162020 @default.
- W3103179916 countsByYear W31031799162021 @default.
- W3103179916 countsByYear W31031799162022 @default.
- W3103179916 crossrefType "proceedings-article" @default.
- W3103179916 hasAuthorship W3103179916A5030468199 @default.
- W3103179916 hasAuthorship W3103179916A5041302228 @default.
- W3103179916 hasAuthorship W3103179916A5047233371 @default.
- W3103179916 hasAuthorship W3103179916A5076775408 @default.
- W3103179916 hasAuthorship W3103179916A5088374525 @default.
- W3103179916 hasBestOaLocation W31031799161 @default.
- W3103179916 hasConcept C107457646 @default.
- W3103179916 hasConcept C154945302 @default.
- W3103179916 hasConcept C15744967 @default.
- W3103179916 hasConcept C188147891 @default.
- W3103179916 hasConcept C2982912361 @default.
- W3103179916 hasConcept C41008148 @default.
- W3103179916 hasConceptScore W3103179916C107457646 @default.
- W3103179916 hasConceptScore W3103179916C154945302 @default.
- W3103179916 hasConceptScore W3103179916C15744967 @default.
- W3103179916 hasConceptScore W3103179916C188147891 @default.
- W3103179916 hasConceptScore W3103179916C2982912361 @default.
- W3103179916 hasConceptScore W3103179916C41008148 @default.
- W3103179916 hasLocation W31031799161 @default.
- W3103179916 hasOpenAccess W3103179916 @default.
- W3103179916 hasPrimaryLocation W31031799161 @default.
- W3103179916 hasRelatedWork W110311947 @default.
- W3103179916 hasRelatedWork W1536570095 @default.
- W3103179916 hasRelatedWork W2007495486 @default.
- W3103179916 hasRelatedWork W2076610045 @default.
- W3103179916 hasRelatedWork W2918883224 @default.
- W3103179916 hasRelatedWork W3005892291 @default.
- W3103179916 hasRelatedWork W4246426965 @default.
- W3103179916 hasRelatedWork W68053931 @default.
- W3103179916 hasRelatedWork W2505387022 @default.
- W3103179916 hasRelatedWork W3106945349 @default.
- W3103179916 isParatext "false" @default.
- W3103179916 isRetracted "false" @default.
- W3103179916 magId "3103179916" @default.
- W3103179916 workType "article" @default.