{"id":"https://openalex.org/W4405785642","doi":"https://doi.org/10.1109/iros58592.2024.10801362","title":"Fixing symbolic plans with reinforcement learning in object-based action spaces","display_name":"Fixing symbolic plans with reinforcement learning in object-based action spaces","publication_year":2024,"publication_date":"2024-10-14","ids":{"openalex":"https://openalex.org/W4405785642","doi":"https://doi.org/10.1109/iros58592.2024.10801362"},"language":"en","primary_location":{"id":"doi:10.1109/iros58592.2024.10801362","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5079601359","display_name":"Christopher Thierauf","orcid":"https://orcid.org/0000-0002-5650-2574"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Christopher Thierauf","raw_affiliation_strings":["Tufts University,Department of Computer Science,Medford,MA,02155"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tufts University,Department of Computer Science,Medford,MA,02155","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5044523801","display_name":"Matthias Scheutz","orcid":"https://orcid.org/0000-0002-0064-2789"},"institutions":[{"id":"https://openalex.org/I121934306","display_name":"Tufts University","ror":"https://ror.org/05wvpxv85","country_code":"US","type":"education","lineage":["https://openalex.org/I121934306"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Matthias Scheutz","raw_affiliation_strings":["Tufts University,Department of Computer Science,Medford,MA,02155"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tufts University,Department of Computer Science,Medford,MA,02155","institution_ids":["https://openalex.org/I121934306"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I121934306"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"12363","last_page":"12369"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11574","display_name":"Artificial Intelligence in Games","score":0.847000002861023,"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/T11574","display_name":"Artificial Intelligence in Games","score":0.847000002861023,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.7879999876022339,"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":0.7354000210762024,"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":0.7140451669692993},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.6402713060379028},{"id":"https://openalex.org/keywords/object","display_name":"Object (grammar)","score":0.5743772983551025},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5740102529525757},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4864940047264099},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.4309675991535187}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7140451669692993},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6402713060379028},{"id":"https://openalex.org/C2781238097","wikidata":"https://www.wikidata.org/wiki/Q175026","display_name":"Object (grammar)","level":2,"score":0.5743772983551025},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5740102529525757},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4864940047264099},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.4309675991535187},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/iros58592.2024.10801362","is_oa":false,"landing_page_url":"https://doi.org/10.1109/iros58592.2024.10801362","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Reduced inequalities","score":0.47999998927116394,"id":"https://metadata.un.org/sdg/10"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1502099479","https://openalex.org/W1917989004","https://openalex.org/W2068127265","https://openalex.org/W2087775928","https://openalex.org/W2097113539","https://openalex.org/W2134831400","https://openalex.org/W2158782408","https://openalex.org/W2164998010","https://openalex.org/W2229480318","https://openalex.org/W2519481221","https://openalex.org/W2534140487","https://openalex.org/W2613865171","https://openalex.org/W2768698792","https://openalex.org/W2949350092","https://openalex.org/W2963709735","https://openalex.org/W2965976698","https://openalex.org/W2967992338","https://openalex.org/W2977520119","https://openalex.org/W3008329436","https://openalex.org/W3037476194","https://openalex.org/W3080814299","https://openalex.org/W3193796809","https://openalex.org/W3214357131","https://openalex.org/W4309549841","https://openalex.org/W4312388059","https://openalex.org/W4313395954","https://openalex.org/W4388617516","https://openalex.org/W6737027161","https://openalex.org/W6748221089","https://openalex.org/W6757333043","https://openalex.org/W6771329031","https://openalex.org/W6851015602","https://openalex.org/W6852055619","https://openalex.org/W6860710830"],"related_works":["https://openalex.org/W4306904969","https://openalex.org/W2138720691","https://openalex.org/W4362501864","https://openalex.org/W4380318855","https://openalex.org/W3084456289","https://openalex.org/W2024136090","https://openalex.org/W4391331176","https://openalex.org/W2031695474","https://openalex.org/W2586732548","https://openalex.org/W2604548540"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1],"techniques":[2],"are":[3,35],"widely":[4],"used":[5],"when":[6],"robots":[7,44,66],"have":[8],"to":[9,45,57,67,70,78,81],"learn":[10,68,71,82],"new":[11],"tasks":[12],"but":[13],"they":[14],"typically":[15],"operate":[16],"on":[17,90],"action":[18],"spaces":[19,34],"defined":[20],"by":[21],"the":[22,25,36,41,59,91],"joints":[23],"of":[24,38,101],"robot.":[26],"We":[27,61],"present":[28],"a":[29,84],"contrasting":[30],"approach":[31],"where":[32],"actions":[33],"trajectories":[37],"objects":[39],"in":[40,83],"environment,":[42],"requiring":[43],"discover":[46],"events":[47],"such":[48],"as":[49],"object":[50],"changes":[51],"and":[52,80],"behaviors":[53],"that":[54,63,74,86],"must":[55],"occur":[56],"accomplish":[58],"task.":[60],"show":[62],"this":[64],"allows":[65],"faster,":[69],"semantic":[72],"representations":[73],"can":[75,105],"be":[76,106],"communicated":[77],"humans,":[79],"manner":[85],"does":[87],"not":[88],"depend":[89],"robot":[92],"itself,":[93],"enabling":[94],"low-cost":[95],"policy":[96],"transfer":[97],"between":[98],"different":[99],"types":[100],"robots.":[102],"Our":[103],"demonstrations":[104],"replicated":[107],"using":[108],"provided":[109],"source":[110],"code":[111],"<sup":[112],"xmlns:mml=\"http://www.w3.org/1998/Math/MathML\"":[113],"xmlns:xlink=\"http://www.w3.org/1999/xlink\">1</sup>.":[114]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}