{"id":"https://openalex.org/W4401414031","doi":"https://doi.org/10.1109/icra57147.2024.10611594","title":"Adapting to the \u201cOpen World\u201d: The Utility of Hybrid Hierarchical Reinforcement Learning and Symbolic Planning","display_name":"Adapting to the \u201cOpen World\u201d: The Utility of Hybrid Hierarchical Reinforcement Learning and Symbolic Planning","publication_year":2024,"publication_date":"2024-05-13","ids":{"openalex":"https://openalex.org/W4401414031","doi":"https://doi.org/10.1109/icra57147.2024.10611594"},"language":"en","primary_location":{"id":"doi:10.1109/icra57147.2024.10611594","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10611594","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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/A5094166137","display_name":"Pierrick Lorang","orcid":null},"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":"Pierrick Lorang","raw_affiliation_strings":["Tufts University,Human-Robot Interaction Laboratory,Medford,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tufts University,Human-Robot Interaction Laboratory,Medford,MA,USA","institution_ids":["https://openalex.org/I121934306"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5110018608","display_name":"H. Horv\u00e1th","orcid":null},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Helmut Horvath","raw_affiliation_strings":["TU Wien,Institute of Information Systems Engineering, Faculty of Informatics, TU Wien,Vienna,Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien,Institute of Information Systems Engineering, Faculty of Informatics, TU Wien,Vienna,Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5106356452","display_name":"Tobias Kietreiber","orcid":null},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Tobias Kietreiber","raw_affiliation_strings":["TU Wien,Institute of Information Systems Engineering, Faculty of Informatics, TU Wien,Vienna,Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien,Institute of Information Systems Engineering, Faculty of Informatics, TU Wien,Vienna,Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5050311128","display_name":"Patrik Zips","orcid":"https://orcid.org/0000-0001-7846-1753"},"institutions":[{"id":"https://openalex.org/I132118926","display_name":"Austrian Institute of Technology","ror":"https://ror.org/04knbh022","country_code":"AT","type":"facility","lineage":["https://openalex.org/I132118926"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Patrik Zips","raw_affiliation_strings":["AIT Austrian Institute of Technology GmbH, Center for Vision, Automation & Control,Vienna,Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AIT Austrian Institute of Technology GmbH, Center for Vision, Automation & Control,Vienna,Austria","institution_ids":["https://openalex.org/I132118926"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037749602","display_name":"Clemens Heitzinger","orcid":"https://orcid.org/0000-0003-1613-5164"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Clemens Heitzinger","raw_affiliation_strings":["TU Wien,Institute of Information Systems Engineering, Faculty of Informatics, TU Wien,Vienna,Austria"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"TU Wien,Institute of Information Systems Engineering, Faculty of Informatics, TU Wien,Vienna,Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"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,Human-Robot Interaction Laboratory,Medford,MA,USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Tufts University,Human-Robot Interaction Laboratory,Medford,MA,USA","institution_ids":["https://openalex.org/I121934306"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"58","issue":null,"first_page":"508","last_page":"514"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9883999824523926,"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/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9883999824523926,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.8318829536437988},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6997060775756836},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4336088001728058}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8318829536437988},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6997060775756836},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4336088001728058}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icra57147.2024.10611594","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/icra57147.2024.10611594","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2024 IEEE International Conference on Robotics and Automation (ICRA)","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":29,"referenced_works":["https://openalex.org/W2060277733","https://openalex.org/W2109910161","https://openalex.org/W2150952649","https://openalex.org/W2337392266","https://openalex.org/W2539402368","https://openalex.org/W2743151379","https://openalex.org/W2907537824","https://openalex.org/W2963709735","https://openalex.org/W2973229164","https://openalex.org/W3007869767","https://openalex.org/W3176303280","https://openalex.org/W3176709420","https://openalex.org/W3200443725","https://openalex.org/W4300126582","https://openalex.org/W4301424984","https://openalex.org/W4306802381","https://openalex.org/W4317439346","https://openalex.org/W6676722073","https://openalex.org/W6745935785","https://openalex.org/W6747473740","https://openalex.org/W6771109905","https://openalex.org/W6772027365","https://openalex.org/W6776801875","https://openalex.org/W6788170692","https://openalex.org/W6801668657","https://openalex.org/W6804601995","https://openalex.org/W6838754243","https://openalex.org/W6846105488","https://openalex.org/W6848839729"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4306904969","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2138720691","https://openalex.org/W2376932109","https://openalex.org/W4362501864","https://openalex.org/W2001405890"],"abstract_inverted_index":{"Open-world":[0],"robotic":[1],"tasks":[2],"such":[3],"as":[4],"autonomous":[5],"driving":[6],"pose":[7],"significant":[8],"challenges":[9],"to":[10,14,35,86,102],"robot":[11],"control":[12],"due":[13],"unknown":[15],"and":[16,40,47,98,105],"unpredictable":[17],"events":[18],"that":[19,80,93],"disrupt":[20],"task":[21],"performance.":[22],"Neural":[23],"network-based":[24],"reinforcement":[25],"learning":[26],"(RL)":[27],"techniques":[28],"(like":[29],"DQN,":[30],"PPO,":[31],"SAC,":[32],"etc.)":[33],"struggle":[34],"adapt":[36,96],"in":[37,54,61],"large":[38],"domains":[39],"suffer":[41],"from":[42],"catastrophic":[43],"forgetting.":[44],"Hybrid":[45],"planning":[46],"RL":[48,104],"approaches":[49],"have":[50],"shown":[51],"some":[52],"promise":[53],"handling":[55],"environmental":[56,113],"changes":[57,114],"but":[58],"lack":[59],"efficiency":[60],"accommodation":[62],"speed.":[63],"To":[64],"address":[65],"this":[66],"limitation,":[67],"we":[68],"propose":[69],"an":[70],"enhanced":[71],"hybrid":[72,106],"system":[73],"with":[74],"a":[75],"nested":[76],"hierarchical":[77],"action":[78],"abstraction":[79],"can":[81,95],"utilize":[82],"previously":[83],"acquired":[84],"skills":[85],"effectively":[87],"tackle":[88],"unexpected":[89],"novelties.":[90],"We":[91],"show":[92],"it":[94],"faster":[97],"generalize":[99],"better":[100],"compared":[101],"state-of-the-art":[103],"approaches,":[107],"significantly":[108],"improving":[109],"robustness":[110],"when":[111],"multiple":[112],"occur":[115],"at":[116],"the":[117],"same":[118],"time.":[119]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}