{"id":"https://openalex.org/W4390897804","doi":"https://doi.org/10.48550/arxiv.2401.06604","title":"Identifying Policy Gradient Subspaces","display_name":"Identifying Policy Gradient Subspaces","publication_year":2024,"publication_date":"2024-01-12","ids":{"openalex":"https://openalex.org/W4390897804","doi":"https://doi.org/10.48550/arxiv.2401.06604"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2401.06604","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.06604","pdf_url":"https://arxiv.org/pdf/2401.06604","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2401.06604","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Schneider, Jan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schneider, Jan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5010207430","display_name":"Pierre Schumacher","orcid":"https://orcid.org/0009-0006-7369-1836"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Schumacher, Pierre","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048792224","display_name":"Simon Guist","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guist, Simon","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100420755","display_name":"Le Chen","orcid":"https://orcid.org/0000-0003-3789-2578"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chen, Le","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064984327","display_name":"Daniel H\u00e4ufle","orcid":"https://orcid.org/0000-0002-3480-6892"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"H\u00e4ufle, Daniel","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044005697","display_name":"Bernhard Sch\u00f6lkopf","orcid":"https://orcid.org/0000-0002-8177-0925"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sch\u00f6lkopf, Bernhard","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5055226918","display_name":"Dieter B\u00fcchler","orcid":"https://orcid.org/0000-0002-2493-0101"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"B\u00fcchler, Dieter","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9973999857902527,"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":0.9973999857902527,"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/T12676","display_name":"Machine Learning and ELM","score":0.9904000163078308,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.9850999712944031,"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":0.8780971765518188},{"id":"https://openalex.org/keywords/subspace-topology","display_name":"Subspace topology","score":0.8414772748947144},{"id":"https://openalex.org/keywords/linear-subspace","display_name":"Linear subspace","score":0.8291552066802979},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7559717893600464},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6792890429496765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5131450295448303},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.45054423809051514},{"id":"https://openalex.org/keywords/trust-region","display_name":"Trust region","score":0.43412649631500244},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.4143165051937103},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.37868523597717285},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.19595745205879211}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8780971765518188},{"id":"https://openalex.org/C32834561","wikidata":"https://www.wikidata.org/wiki/Q660730","display_name":"Subspace topology","level":2,"score":0.8414772748947144},{"id":"https://openalex.org/C12362212","wikidata":"https://www.wikidata.org/wiki/Q728435","display_name":"Linear subspace","level":2,"score":0.8291552066802979},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7559717893600464},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6792890429496765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5131450295448303},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.45054423809051514},{"id":"https://openalex.org/C89109886","wikidata":"https://www.wikidata.org/wiki/Q1535924","display_name":"Trust region","level":3,"score":0.43412649631500244},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.4143165051937103},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.37868523597717285},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.19595745205879211},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"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/C178635117","wikidata":"https://www.wikidata.org/wiki/Q747499","display_name":"RADIUS","level":2,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2401.06604","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.06604","pdf_url":"https://arxiv.org/pdf/2401.06604","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2401.06604","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2401.06604","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2401.06604","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2401.06604","pdf_url":"https://arxiv.org/pdf/2401.06604","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4390897804.pdf","grobid_xml":"https://content.openalex.org/works/W4390897804.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3100286349","https://openalex.org/W2896134808","https://openalex.org/W4294291164","https://openalex.org/W3172436493","https://openalex.org/W1887135636","https://openalex.org/W4287164812","https://openalex.org/W1983112127","https://openalex.org/W2386063599","https://openalex.org/W1975884855","https://openalex.org/W2018064504"],"abstract_inverted_index":{"Policy":[0],"gradient":[1,64,78],"methods":[2,65],"hold":[3],"great":[4],"potential":[5],"for":[6,59,95],"solving":[7],"complex":[8],"continuous":[9],"control":[10],"tasks.":[11,70],"Still,":[12],"their":[13],"training":[14],"efficiency":[15],"can":[16,32],"be":[17,33],"improved":[18],"by":[19,35],"exploiting":[20],"structure":[21],"within":[22],"the":[23,37,74,81],"optimization":[24],"problem.":[25],"Recent":[26],"work":[27,97],"indicates":[28],"that":[29,39],"supervised":[30],"learning":[31],"accelerated":[34],"leveraging":[36],"fact":[38],"gradients":[40],"lie":[41],"in":[42],"a":[43,53],"low-dimensional":[44],"and":[45],"slowly-changing":[46],"subspace.":[47],"In":[48],"this":[49,57],"paper,":[50],"we":[51],"conduct":[52],"thorough":[54],"evaluation":[55],"of":[56,76],"phenomenon":[58],"two":[60],"popular":[61],"deep":[62],"policy":[63],"on":[66,98],"various":[67],"simulated":[68],"benchmark":[69],"Our":[71],"results":[72],"demonstrate":[73],"existence":[75],"such":[77],"subspaces":[79],"despite":[80],"continuously":[82],"changing":[83],"data":[84],"distribution":[85],"inherent":[86],"to":[87],"reinforcement":[88,101],"learning.":[89],"These":[90],"findings":[91],"reveal":[92],"promising":[93],"directions":[94],"future":[96],"more":[99],"efficient":[100],"learning,":[102],"e.g.,":[103],"through":[104],"improving":[105],"parameter-space":[106],"exploration":[107],"or":[108],"enabling":[109],"second-order":[110],"optimization.":[111]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-08-22T07:34:49.880490","created_date":"2025-10-10T00:00:00"}