Deep Reinforcement Learning of Abstract Reasoning from Demonstrations
Extracting a set of generalizable rules that govern the dynamics of complex, high-level interactions between humans based only on observations is a high-level cognitive ability. Mastery of this skill marks a significant milestone in the human developmental process. A key challenge in designing such...
Uložené v:
| Vydané v: | 2018 13th ACM/IEEE International Conference on Human-Robot Interaction (HRI) s. 160 - 168 |
|---|---|
| Hlavní autori: | , |
| Médium: | Konferenčný príspevok.. |
| Jazyk: | English |
| Vydavateľské údaje: |
New York, NY, USA
ACM
26.02.2018
|
| Edícia: | ACM Conferences |
| Predmet: | |
| ISBN: | 9781450349536, 1450349536 |
| ISSN: | 2167-2148 |
| On-line prístup: | Získať plný text |
| Tagy: |
Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
|
| Abstract | Extracting a set of generalizable rules that govern the dynamics of complex, high-level interactions between humans based only on observations is a high-level cognitive ability. Mastery of this skill marks a significant milestone in the human developmental process. A key challenge in designing such an ability in autonomous robots is discovering the relationships among discriminatory features. Identifying features in natural scenes that are representative of a particular event or interaction (i.e. »discriminatory features») and then discovering the relationships (e.g., temporal/spatial/spatio-temporal/causal) among those features in the form of generalized rules are non-trivial problems. They often appear as a »chicken-and-egg» dilemma. This paper proposes an end-to-end learning framework to tackle these two problems in the context of learning generalized, high-level rules of human interactions from structured demonstrations. We employed our proposed deep reinforcement learning framework to learn a set of rules that govern a behavioral intervention session between two agents based on observations of several instances of the session. We also tested the accuracy of our framework with human subjects in diverse situations. |
|---|---|
| AbstractList | Extracting a set of generalizable rules that govern the dynamics of complex, high-level interactions between humans based only on observations is a high-level cognitive ability. Mastery of this skill marks a significant milestone in the human developmental process. A key challenge in designing such an ability in autonomous robots is discovering the relationships among discriminatory features. Identifying features in natural scenes that are representative of a particular event or interaction (i.e. »discriminatory features») and then discovering the relationships (e.g., temporal/spatial/spatio-temporal/causal) among those features in the form of generalized rules are non-trivial problems. They often appear as a »chicken-and-egg» dilemma. This paper proposes an end-to-end learning framework to tackle these two problems in the context of learning generalized, high-level rules of human interactions from structured demonstrations. We employed our proposed deep reinforcement learning framework to learn a set of rules that govern a behavioral intervention session between two agents based on observations of several instances of the session. We also tested the accuracy of our framework with human subjects in diverse situations. Extracting a set of generalizable rules that govern the dynamics of complex, high-level interactions between humans based only on observations is a high-level cognitive ability. Mastery of this skill marks a significant milestone in the human developmental process. A key challenge in designing such an ability in autonomous robots is discovering the relationships among discriminatory features. Identifying features in natural scenes that are representative of a particular event or interaction (i.e. 'discriminatory features') and then discovering the relationships (e.g., temporal/spatial/spatiotemporal/causal) among those features in the form of generalized rules are non-trivial problems. They often appear as a 'chicken-and-egg' dilemma. This paper proposes an end-to-end learning framework to tackle these two problems in the context of learning generalized, high-level rules of human interactions from structured demonstrations. We employed our proposed deep reinforcement learning framework to learn a set of rules that govern a behavioral intervention session between two agents based on observations of several instances of the session. We also tested the accuracy of our framework with human subjects in diverse situations. |
| Author | Clark-Turner, Madison Begum, Momotaz |
| Author_xml | – sequence: 1 givenname: Madison surname: Clark-Turner fullname: Clark-Turner, Madison email: mbc2004@cs.unh.edu organization: University of New Hampshire, Durham, NH, USA – sequence: 2 givenname: Momotaz surname: Begum fullname: Begum, Momotaz email: mbegum@cs.unh.edu organization: University of New Hampshire, Durham, NH, USA |
| BookMark | eNqNkDtPwzAUhc1LopTMDCwZWRL8ih9j1ZaHVAkJwWzZ7jUKELtysvDvSdtMTExHut899x6dK3QeUwSEbgiuCeHNPSOSUErqgyp9ggot1Qgw47ph4hTNKBGyooSrsz_sEhV9_4kxphIzJukMrVcAu_IV2hhS9tBBHMoN2Bzb-FGmUC5cP2Trh3HF9ukwDTl15Qq6FPdoaEe9RhfBfvdQTDpH7w_rt-VTtXl5fF4uNpWlXA4VIR6Pj0ECCKeUpr6hfswXBLXBglRbvXWS661yQigBjjW4AZAiNJ4Hydgc3R7vtgBgdrntbP4xmkvG1Z7WR2p9Z1xKX70h2Ow7M1NnZurMuNxCGA13_zSwX-ikaME |
| ContentType | Conference Proceeding |
| Copyright | 2018 ACM |
| Copyright_xml | – notice: 2018 ACM |
| DBID | 6IE 6IL CBEJK RIE RIL |
| DOI | 10.1145/3171221.3171289 |
| DatabaseName | IEEE Electronic Library (IEL) Conference Proceedings IEEE Xplore POP ALL IEEE Xplore All Conference Proceedings IEEE/IET Electronic Library (IEL) (UW System Shared) IEEE Proceedings Order Plans (POP All) 1998-Present |
| DatabaseTitleList | |
| Database_xml | – sequence: 1 dbid: RIE name: IEEE/IET Electronic Library (IEL) (UW System Shared) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering |
| EISBN | 9781450349536 1450349536 |
| EISSN | 2167-2148 |
| EndPage | 168 |
| ExternalDocumentID | 9473483 |
| Genre | orig-research |
| GrantInformation_xml | – fundername: National Science Foundation funderid: 10.13039/100000001 |
| GroupedDBID | 6IE 6IF 6IL 6IN ABLEC ACM ADPZR ALMA_UNASSIGNED_HOLDINGS APO BEFXN BFFAM BGNUA BKEBE BPEOZ CBEJK GUFHI IEGSK OCL RIE RIL AAWTH ADZIZ CHZPO |
| ID | FETCH-LOGICAL-a247t-11c0703e7ee6b8892c52c781f62afae78d9db749d8b6686eb3505ee76f5c4f733 |
| IEDL.DBID | RIE |
| ISBN | 9781450349536 1450349536 |
| ISICitedReferencesCount | 8 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000460476300021&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| IngestDate | Wed Aug 27 02:26:24 EDT 2025 Wed Jan 31 06:41:50 EST 2024 |
| IsPeerReviewed | false |
| IsScholarly | false |
| Keywords | deep learning abstract reasoning learning from demonstration |
| Language | English |
| License | Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from Permissions@acm.org |
| LinkModel | DirectLink |
| MeetingName | HRI '18: ACM/IEEE International Conference on Human-Robot Interaction |
| MergedId | FETCHMERGED-LOGICAL-a247t-11c0703e7ee6b8892c52c781f62afae78d9db749d8b6686eb3505ee76f5c4f733 |
| PageCount | 9 |
| ParticipantIDs | acm_books_10_1145_3171221_3171289_brief ieee_primary_9473483 acm_books_10_1145_3171221_3171289 |
| PublicationCentury | 2000 |
| PublicationDate | 20180226 2018-March-25 |
| PublicationDateYYYYMMDD | 2018-02-26 2018-03-25 |
| PublicationDate_xml | – month: 02 year: 2018 text: 20180226 day: 26 |
| PublicationDecade | 2010 |
| PublicationPlace | New York, NY, USA |
| PublicationPlace_xml | – name: New York, NY, USA |
| PublicationSeriesTitle | ACM Conferences |
| PublicationTitle | 2018 13th ACM/IEEE International Conference on Human-Robot Interaction (HRI) |
| PublicationTitleAbbrev | HRI |
| PublicationYear | 2018 |
| Publisher | ACM |
| Publisher_xml | – name: ACM |
| SSID | ssj0002703372 ssj0003204102 |
| Score | 1.7228613 |
| Snippet | Extracting a set of generalizable rules that govern the dynamics of complex, high-level interactions between humans based only on observations is a high-level... |
| SourceID | ieee acm |
| SourceType | Publisher |
| StartPage | 160 |
| SubjectTerms | Abstract Reasoning Analytical models Cognition Computing methodologies -- Artificial intelligence -- Computer vision -- Computer vision tasks -- Vision for robotics Computing methodologies -- Artificial intelligence -- Knowledge representation and reasoning Computing methodologies -- Artificial intelligence -- Knowledge representation and reasoning -- Cognitive robotics Computing methodologies -- Machine learning -- Learning paradigms -- Supervised learning Deep Learning Human-robot interaction Learning from Demonstration Object recognition Probabilistic logic Reinforcement learning Theory of computation -- Logic -- Abstraction Theory of computation -- Logic -- Automated reasoning Training |
| Title | Deep Reinforcement Learning of Abstract Reasoning from Demonstrations |
| URI | https://ieeexplore.ieee.org/document/9473483 |
| WOSCitedRecordID | wos000460476300021&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LSwMxEA5t8aAXH61aX0QQvLht806OYls8lSIKvS272VnpoQ-6W3-_SXapCoJ42UcYluVjwkwm-b5B6A70IM2UZRGXqbsAG0QaMh0Jzg2DhAvD8tBsQk0mejYz0wZ62HFhACAcPoOefwx7-dnKbn2prG-412JhTdRUSlZcrV09hTrXZTUH1L8zOuDEH945qwRxRd9FSkIp6YW7b-veTOziR1OVEFPGh__7myPU-SLn4eku7ByjBixP0ME3XcE2Gg0B1vgFgiqqDQVAXAupvuNVjh9TX-CwpTNJilCPxZ5mgoew8Oli5RRFB72NR69Pz1HdLyFKKFdlRIj1ExgUgEy1NtQKapUmuaRJnoDSmclSxU2mUym1dMtol_4AKJkLy3PF2ClqLVdLOEdYEumVzoiVqeBJRnSunL2gxsvjW5F30a0DL_YLgSKuuM0irgGOa4C76P5PmzjdzMF9re3hjdeVwEZcI3vx-_Al2ndZSyAGUnGFWuVmC9doz36U82JzE7ziE6LosSc |
| linkProvider | IEEE |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1LS8NAEB5sFdSLj1atzwiCF9N235uj-KBiLSIKvYVkMxEPtqVN_f3ubkJVEMRLHssQwjDLzM7u930AZ6i7aaYMC7lM7QVZN9SY6VBwHjFMuIhY7sUm1GCgh8PocQkuFlgYRPSHz7DtHv1efjY2c9cq60TccbGwGiw75awKrbXoqFAbvKxCgbp3RrucuOM7uyUlrujYXEkoJW1_d8LutcS8_5BV8VnlduN__7MJzS94XvC4SDxbsISjbVj_xizYgJtrxEnwhJ4X1fgWYFBRqb4G4zy4TF2LwxTWJJn5jmzggCbBNb67grEMi1kTXm5vnq96YaWYECaUqyIkxLgpjApRplpH1AhqlCa5pEmeoNJZlKWKR5lOpdTSLqRtAYSoZC4MzxVjO1AfjUe4B4Ek0nGdESNTwZOM6FxZe0EjR5BvRN6CU-u82C0FZnGJbhZx5eC4cnALzv-0idPpG9qvNZx740lJsRFXnt3_ffgEVnvPD_24fze4P4A1W8N4mCAVh1AvpnM8ghXzUbzNpsc-Qj4BEUe0cA |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Abook&rft.genre=proceeding&rft.title=2018+13th+ACM%2FIEEE+International+Conference+on+Human-Robot+Interaction+%28HRI%29&rft.atitle=Deep+Reinforcement+Learning+of+Abstract+Reasoning+from+Demonstrations&rft.au=Clark-Turner%2C+Madison&rft.au=Begum%2C+Momotaz&rft.date=2018-03-25&rft.pub=ACM&rft.eissn=2167-2148&rft.spage=160&rft.epage=168&rft_id=info:doi/10.1145%2F3171221.3171289&rft.externalDocID=9473483 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9781450349536/lc.gif&client=summon&freeimage=true |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9781450349536/mc.gif&client=summon&freeimage=true |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=9781450349536/sc.gif&client=summon&freeimage=true |