{"id":"https://openalex.org/W4390188019","doi":"https://doi.org/10.1109/icdl55364.2023.10364407","title":"A Closer Look at Reward Decomposition for High-Level Robotic Explanations","display_name":"A Closer Look at Reward Decomposition for High-Level Robotic Explanations","publication_year":2023,"publication_date":"2023-11-09","ids":{"openalex":"https://openalex.org/W4390188019","doi":"https://doi.org/10.1109/icdl55364.2023.10364407"},"language":"en","primary_location":{"id":"doi:10.1109/icdl55364.2023.10364407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl55364.2023.10364407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023237216","display_name":"Wenhao Lu","orcid":"https://orcid.org/0000-0001-8660-2886"},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]},{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":true,"raw_author_name":"Wenhao Lu","raw_affiliation_strings":["University of Hamburg,Knowledge Technology Group,Department of Informatics","Department of Informatics, Knowledge Technology Group, University of Hamburg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hamburg,Knowledge Technology Group,Department of Informatics","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]},{"raw_affiliation_string":"Department of Informatics, Knowledge Technology Group, University of Hamburg","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103057571","display_name":"Xufeng Zhao","orcid":"https://orcid.org/0009-0001-6972-5048"},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]},{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Xufeng Zhao","raw_affiliation_strings":["University of Hamburg,Knowledge Technology Group,Department of Informatics","Department of Informatics, Knowledge Technology Group, University of Hamburg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hamburg,Knowledge Technology Group,Department of Informatics","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]},{"raw_affiliation_string":"Department of Informatics, Knowledge Technology Group, University of Hamburg","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5015567592","display_name":"Sven Magg","orcid":"https://orcid.org/0000-0002-0589-6585"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sven Magg","raw_affiliation_strings":["Hamburger Informatik Technologie-Center e.V. (HITeC)"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Hamburger Informatik Technologie-Center e.V. (HITeC)","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5066789231","display_name":"Martin Gromniak","orcid":"https://orcid.org/0000-0002-6602-8685"},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]},{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Martin Gromniak","raw_affiliation_strings":["University of Hamburg,Knowledge Technology Group,Department of Informatics","Department of Informatics, Knowledge Technology Group, University of Hamburg","ZAL Center of Applied Aeronautical Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hamburg,Knowledge Technology Group,Department of Informatics","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]},{"raw_affiliation_string":"Department of Informatics, Knowledge Technology Group, University of Hamburg","institution_ids":["https://openalex.org/I159176309"]},{"raw_affiliation_string":"ZAL Center of Applied Aeronautical Research","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100606513","display_name":"Mengdi Li","orcid":"https://orcid.org/0009-0000-2650-2891"},"institutions":[{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]},{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Mengdi Li","raw_affiliation_strings":["University of Hamburg,Knowledge Technology Group,Department of Informatics","Department of Informatics, Knowledge Technology Group, University of Hamburg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hamburg,Knowledge Technology Group,Department of Informatics","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]},{"raw_affiliation_string":"Department of Informatics, Knowledge Technology Group, University of Hamburg","institution_ids":["https://openalex.org/I159176309"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033486668","display_name":"Stefan Wermter","orcid":"https://orcid.org/0000-0003-1343-4775"},"institutions":[{"id":"https://openalex.org/I884043246","display_name":"Hamburg University of Technology","ror":"https://ror.org/04bs1pb34","country_code":"DE","type":"education","lineage":["https://openalex.org/I884043246"]},{"id":"https://openalex.org/I159176309","display_name":"Universit\u00e4t Hamburg","ror":"https://ror.org/00g30e956","country_code":"DE","type":"education","lineage":["https://openalex.org/I159176309"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Stefan Wermter","raw_affiliation_strings":["University of Hamburg,Knowledge Technology Group,Department of Informatics","Department of Informatics, Knowledge Technology Group, University of Hamburg"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Hamburg,Knowledge Technology Group,Department of Informatics","institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"]},{"raw_affiliation_string":"Department of Informatics, Knowledge Technology Group, University of Hamburg","institution_ids":["https://openalex.org/I159176309"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5023237216"],"corresponding_institution_ids":["https://openalex.org/I159176309","https://openalex.org/I884043246"],"apc_list":null,"apc_paid":null,"fwci":1.0175,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8186118,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"429","last_page":"436"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.9988999962806702,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9912999868392944,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9897000193595886,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7364414930343628},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.655621349811554},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.6266794204711914},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.6128309369087219},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6070060729980469},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5803195238113403},{"id":"https://openalex.org/keywords/transparency","display_name":"Transparency (behavior)","score":0.578942060470581},{"id":"https://openalex.org/keywords/decomposition","display_name":"Decomposition","score":0.5329607129096985},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.44791093468666077},{"id":"https://openalex.org/keywords/cognitive-science","display_name":"Cognitive science","score":0.34339892864227295},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.11679646372795105}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7364414930343628},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.655621349811554},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6266794204711914},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.6128309369087219},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6070060729980469},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5803195238113403},{"id":"https://openalex.org/C2780233690","wikidata":"https://www.wikidata.org/wiki/Q535347","display_name":"Transparency (behavior)","level":2,"score":0.578942060470581},{"id":"https://openalex.org/C124681953","wikidata":"https://www.wikidata.org/wiki/Q339062","display_name":"Decomposition","level":2,"score":0.5329607129096985},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44791093468666077},{"id":"https://openalex.org/C188147891","wikidata":"https://www.wikidata.org/wiki/Q147638","display_name":"Cognitive science","level":1,"score":0.34339892864227295},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.11679646372795105},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icdl55364.2023.10364407","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icdl55364.2023.10364407","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Development and Learning (ICDL)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":58,"referenced_works":["https://openalex.org/W1806263934","https://openalex.org/W1901129140","https://openalex.org/W1903029394","https://openalex.org/W2145339207","https://openalex.org/W2334782222","https://openalex.org/W2615547864","https://openalex.org/W2765615734","https://openalex.org/W2891830784","https://openalex.org/W2962702317","https://openalex.org/W2962746398","https://openalex.org/W2962793652","https://openalex.org/W2963733622","https://openalex.org/W2964227312","https://openalex.org/W2981731882","https://openalex.org/W2995372147","https://openalex.org/W2996457711","https://openalex.org/W3011120880","https://openalex.org/W3116073702","https://openalex.org/W3128894241","https://openalex.org/W3204657926","https://openalex.org/W3210940825","https://openalex.org/W4221143046","https://openalex.org/W4224912544","https://openalex.org/W4225947020","https://openalex.org/W4246252528","https://openalex.org/W4288043501","https://openalex.org/W4292779060","https://openalex.org/W4297675755","https://openalex.org/W4308804331","https://openalex.org/W4309183395","https://openalex.org/W4312884538","https://openalex.org/W4316662143","https://openalex.org/W4360836968","https://openalex.org/W4389665575","https://openalex.org/W6640054144","https://openalex.org/W6680080562","https://openalex.org/W6727349600","https://openalex.org/W6728458142","https://openalex.org/W6730153900","https://openalex.org/W6744542307","https://openalex.org/W6744991969","https://openalex.org/W6750391026","https://openalex.org/W6754454578","https://openalex.org/W6771668669","https://openalex.org/W6771935241","https://openalex.org/W6775686901","https://openalex.org/W6778883912","https://openalex.org/W6783003186","https://openalex.org/W6785308759","https://openalex.org/W6787348641","https://openalex.org/W6797487168","https://openalex.org/W6802397740","https://openalex.org/W6809646742","https://openalex.org/W6810640255","https://openalex.org/W6838836974","https://openalex.org/W6841586102","https://openalex.org/W6843357306","https://openalex.org/W6847069948"],"related_works":["https://openalex.org/W3081288631","https://openalex.org/W3152382318","https://openalex.org/W3004686567","https://openalex.org/W2738656338","https://openalex.org/W2603787370","https://openalex.org/W2555400967","https://openalex.org/W3214759741","https://openalex.org/W3174876210","https://openalex.org/W2388458847","https://openalex.org/W3126697728"],"abstract_inverted_index":{"Explaining":[0],"the":[1,44,53,72,78,112,116,151],"behaviour":[2,47],"of":[3,55,82,118,126,138,153],"intelligent":[4],"agents":[5,34],"learned":[6],"by":[7],"reinforcement":[8],"learning":[9,90],"(RL)":[10],"to":[11,18,41,52,65,146],"humans":[12,145],"is":[13],"challenging":[14],"yet":[15],"crucial":[16],"due":[17],"their":[19],"incomprehensible":[20],"proprioceptive":[21],"states,":[22],"variational":[23],"intermediate":[24],"goals,":[25],"and":[26,80,104,123,132,164],"resultant":[27],"unpredictability.":[28],"Moreover,":[29],"one-step":[30],"explanations":[31,70,106],"for":[32,43,102,144,162],"RL":[33],"can":[35],"be":[36],"ambiguous":[37],"as":[38],"they":[39],"fail":[40],"account":[42],"agent's":[45],"future":[46],"at":[48],"each":[49],"transition,":[50],"adding":[51],"complexity":[54],"explaining":[56],"robot":[57],"actions.":[58],"By":[59],"leveraging":[60],"abstracted":[61,98],"actions":[62],"that":[63,92,141],"map":[64],"task-specific":[66],"primitives,":[67],"we":[68,85,149],"avoid":[69],"on":[71,108],"movement":[73],"level.":[74],"To":[75],"further":[76],"improve":[77],"transparency":[79],"explainability":[81],"robotic":[83,128],"systems,":[84],"propose":[86],"an":[87],"explainable":[88],"Q-Map":[89],"framework":[91,120],"combines":[93],"reward":[94],"decomposition":[95],"(RD)":[96],"with":[97,157],"action":[99],"spaces,":[100],"allowing":[101],"non-ambiguous":[103],"high-level":[105],"based":[107],"object":[109],"properties":[110],"in":[111],"task.":[113],"We":[114],"demonstrate":[115,150],"effectiveness":[117],"our":[119],"through":[121],"quantitative":[122],"qualitative":[124],"analysis":[125],"two":[127],"scenarios,":[129],"showcasing":[130],"visual":[131],"textual":[133],"explanations,":[134,140],"from":[135],"output":[136],"artefacts":[137,156],"RD":[139],"are":[142],"easy":[143],"comprehend.":[147],"Additionally,":[148],"versatility":[152],"integrating":[154],"these":[155],"large":[158],"language":[159],"models":[160],"(LLMs)":[161],"reasoning":[163],"interactive":[165],"querying.":[166]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2026-05-02T08:42:23.175194","created_date":"2025-10-10T00:00:00"}