{"id":"https://openalex.org/W3181438924","doi":"https://doi.org/10.14428/esann/2021.es2021-83","title":"Behavior Constraining in Weight Space for Offline Reinforcement Learning","display_name":"Behavior Constraining in Weight Space for Offline Reinforcement Learning","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3181438924","doi":"https://doi.org/10.14428/esann/2021.es2021-83","mag":"3181438924"},"language":"en","primary_location":{"id":"doi:10.14428/esann/2021.es2021-83","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2021.es2021-83","pdf_url":"https://doi.org/10.14428/esann/2021.es2021-83","source":{"id":"https://openalex.org/S4306509709","display_name":"ESANN 2021 proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2021 proceedings","raw_type":"proceedings-article"},"type":"preprint","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"bronze","oa_url":"https://doi.org/10.14428/esann/2021.es2021-83","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5005487112","display_name":"Phillip Swazinna","orcid":"https://orcid.org/0000-0003-4667-9584"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Phillip Swazinna","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035246650","display_name":"Steffen Udluft","orcid":"https://orcid.org/0000-0002-5767-2591"},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Steffen Udluft","raw_affiliation_strings":[") Siemens Technology -Learning Systems -Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":") Siemens Technology -Learning Systems -Germany","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060543628","display_name":"Daniel Hein","orcid":"https://orcid.org/0000-0002-8375-1592"},"institutions":[{"id":"https://openalex.org/I1325886976","display_name":"Siemens (Germany)","ror":"https://ror.org/059mq0909","country_code":"DE","type":"company","lineage":["https://openalex.org/I1325886976"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Daniel Hein","raw_affiliation_strings":[") Siemens Technology -Learning Systems -Germany"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":") Siemens Technology -Learning Systems -Germany","institution_ids":["https://openalex.org/I1325886976"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002518694","display_name":"Thomas A. Runkler","orcid":"https://orcid.org/0000-0002-5465-198X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Thomas Runkler","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":{"value":0.09194834,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"329","last_page":"334"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.973800003528595,"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":0.973800003528595,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.942799985408783,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.9315999746322632,"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":0.9006472826004028},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.7010005712509155},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.6819628477096558},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6436795592308044},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6433373689651489},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5633798241615295},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5284899473190308},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4882517158985138},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09813335537910461},{"id":"https://openalex.org/keywords/social-psychology","display_name":"Social psychology","score":0.06868654489517212}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.9006472826004028},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.7010005712509155},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.6819628477096558},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6436795592308044},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6433373689651489},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5633798241615295},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5284899473190308},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4882517158985138},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09813335537910461},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.06868654489517212},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.14428/esann/2021.es2021-83","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2021.es2021-83","pdf_url":"https://doi.org/10.14428/esann/2021.es2021-83","source":{"id":"https://openalex.org/S4306509709","display_name":"ESANN 2021 proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2021 proceedings","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2107.05479","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2107.05479","pdf_url":"https://arxiv.org/pdf/2107.05479","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"","raw_type":"text"},{"id":"mag:3181438924","is_oa":true,"landing_page_url":"https://arxiv.org/pdf/2107.05479v1","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2107.05479","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2107.05479","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"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":"doi:10.14428/esann/2021.es2021-83","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2021.es2021-83","pdf_url":"https://doi.org/10.14428/esann/2021.es2021-83","source":{"id":"https://openalex.org/S4306509709","display_name":"ESANN 2021 proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2021 proceedings","raw_type":"proceedings-article"},"sustainable_development_goals":[{"display_name":"Peace, Justice and strong institutions","score":0.7300000190734863,"id":"https://metadata.un.org/sdg/16"}],"awards":[{"id":"https://openalex.org/G4468305794","display_name":null,"funder_award_id":"01IS18049A","funder_id":"https://openalex.org/F4320321114","funder_display_name":"Bundesministerium f\u00fcr Bildung und Forschung"}],"funders":[{"id":"https://openalex.org/F4320321114","display_name":"Bundesministerium f\u00fcr Bildung und Forschung","ror":"https://ror.org/04pz7b180"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3181438924.pdf","grobid_xml":"https://content.openalex.org/works/W3181438924.grobid-xml"},"referenced_works_count":8,"referenced_works":["https://openalex.org/W2728455196","https://openalex.org/W2760661167","https://openalex.org/W2904453761","https://openalex.org/W2947150733","https://openalex.org/W2991355586","https://openalex.org/W3048481719","https://openalex.org/W6677916085","https://openalex.org/W6732665253"],"related_works":["https://openalex.org/W3207240768","https://openalex.org/W3126916000","https://openalex.org/W3122329924","https://openalex.org/W3203183716","https://openalex.org/W3205794883","https://openalex.org/W3130718980","https://openalex.org/W3129049380","https://openalex.org/W3207335863","https://openalex.org/W3209701532","https://openalex.org/W3199737839","https://openalex.org/W3135865540","https://openalex.org/W3127984962","https://openalex.org/W3179772193","https://openalex.org/W2904453761","https://openalex.org/W3209208698","https://openalex.org/W3206246732","https://openalex.org/W3129049565","https://openalex.org/W2735325244","https://openalex.org/W3168236455","https://openalex.org/W3214094365"],"abstract_inverted_index":{"In":[0],"offline":[1],"reinforcement":[2],"learning,":[3],"a":[4,11,32,36,48],"policy":[5,54],"needs":[6],"to":[7,22,25],"be":[8],"learned":[9],"from":[10],"single":[12],"pre-collected":[13],"dataset.":[14],"Typically,":[15],"policies":[16],"are":[17],"thus":[18],"regularized":[19],"during":[20],"training":[21],"behave":[23],"similarly":[24],"the":[26,53],"data":[27],"generating":[28,42],"policy,":[29],"by":[30],"adding":[31],"penalty":[33],"based":[34],"on":[35],"divergence":[37],"between":[38],"action":[39],"distributions":[40],"of":[41],"and":[43,61],"trained":[44],"policy.":[45],"We":[46],"propose":[47],"new":[49],"algorithm,":[50],"which":[51],"constrains":[52],"directly":[55],"in":[56,65],"its":[57,63],"weight":[58],"space":[59],"instead,":[60],"demonstrate":[62],"effectiveness":[64],"experiments.":[66]},"counts_by_year":[],"updated_date":"2026-07-01T08:55:40.977307","created_date":"2025-10-10T00:00:00"}