{"id":"https://openalex.org/W4409479689","doi":"https://doi.org/10.14428/esann/2025.es2025-114","title":"TEA: Trajectory Encoding Augmentation for Robust and Transferable Policies in Offline Reinforcement Learning","display_name":"TEA: Trajectory Encoding Augmentation for Robust and Transferable Policies in Offline Reinforcement Learning","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W4409479689","doi":"https://doi.org/10.14428/esann/2025.es2025-114"},"language":"en","primary_location":{"id":"doi:10.14428/esann/2025.es2025-114","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2025.es2025-114","pdf_url":"https://doi.org/10.14428/esann/2025.es2025-114","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2025 proceesdings","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.14428/esann/2025.es2025-114","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5115002455","display_name":"Bat\u0131kan Bora Ormanc\u0131","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bat\u0131kan Bora Ormanc\u0131","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","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":[],"countries":[],"is_corresponding":false,"raw_author_name":"Steffen Udluft","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"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":0,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":1.7588,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.86027329,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"353","last_page":"358"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9158999919891357,"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":0.9158999919891357,"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":0.778798520565033},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.7570188045501709},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.7520686388015747},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6529051661491394},{"id":"https://openalex.org/keywords/reinforcement","display_name":"Reinforcement","score":0.6220369935035706},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3771964907646179},{"id":"https://openalex.org/keywords/structural-engineering","display_name":"Structural engineering","score":0.12061002850532532},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11796402931213379}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.778798520565033},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.7570188045501709},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.7520686388015747},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6529051661491394},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.6220369935035706},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3771964907646179},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.12061002850532532},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11796402931213379},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C1276947","wikidata":"https://www.wikidata.org/wiki/Q333","display_name":"Astronomy","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.14428/esann/2025.es2025-114","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2025.es2025-114","pdf_url":"https://doi.org/10.14428/esann/2025.es2025-114","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2025 proceesdings","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.14428/esann/2025.es2025-114","is_oa":true,"landing_page_url":"https://doi.org/10.14428/esann/2025.es2025-114","pdf_url":"https://doi.org/10.14428/esann/2025.es2025-114","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ESANN 2025 proceesdings","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"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/W4409479689.pdf","grobid_xml":"https://content.openalex.org/works/W4409479689.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4310083477","https://openalex.org/W2328553770","https://openalex.org/W2920061524","https://openalex.org/W1977959518","https://openalex.org/W2038908348","https://openalex.org/W2107890255","https://openalex.org/W2106552856","https://openalex.org/W2145821588","https://openalex.org/W2086122291","https://openalex.org/W1987513656"],"abstract_inverted_index":{"In":[0],"this":[1],"paper,":[2],"we":[3],"investigate":[4],"offline":[5],"reinforcement":[6],"learning":[7],"(RL)":[8],"with":[9,23,59,71],"the":[10,36,62],"goal":[11],"of":[12,43,64],"training":[13],"a":[14,27,65],"single":[15,66],"robust":[16],"policy":[17,67],"that":[18,55,76,84],"generalizes":[19],"effectively":[20,95],"across":[21,96],"environments":[22,70],"unseen":[24],"dynamics.We":[25],"propose":[26],"novel":[28,69],"approach,":[29],"Trajectory":[30],"Encoding":[31],"Augmentation":[32],"(TEA),":[33],"which":[34],"extends":[35],"state":[37],"space":[38],"by":[39],"integrating":[40],"latent":[41],"representations":[42],"environmental":[44],"dynamics":[45],"obtained":[46],"from":[47],"sequence":[48],"encoders,":[49],"such":[50],"as":[51],"autoencoders.Our":[52],"findings":[53],"show":[54],"incorporating":[56],"these":[57],"encodings":[58],"TEA":[60,85],"improves":[61],"transferability":[63],"to":[68,93],"new":[72],"dynamics,":[73],"surpassing":[74],"methods":[75],"rely":[77],"solely":[78],"on":[79],"unmodified":[80],"states.These":[81],"results":[82],"indicate":[83],"captures":[86],"critical,":[87],"environment-specific":[88],"characteristics,":[89],"enabling":[90],"RL":[91],"agents":[92],"generalize":[94],"dynamic":[97],"conditions.":[98]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}