{"id":"https://openalex.org/W4416112411","doi":"https://doi.org/10.48550/arxiv.2503.04074","title":"Can We Optimize Deep RL Policy Weights as Trajectory Modeling?","display_name":"Can We Optimize Deep RL Policy Weights as Trajectory Modeling?","publication_year":2025,"publication_date":"2025-03-06","ids":{"openalex":"https://openalex.org/W4416112411","doi":"https://doi.org/10.48550/arxiv.2503.04074"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2503.04074","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.04074","pdf_url":"https://arxiv.org/pdf/2503.04074","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/2503.04074","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103176048","display_name":"Hongyao Tang","orcid":"https://orcid.org/0000-0001-7478-7684"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Tang, Hongyao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5103176048"],"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":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":0.35589998960494995,"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":0.35589998960494995,"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":0.19699999690055847,"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/T10775","display_name":"Generative Adversarial Networks and Image Synthesis","score":0.09640000015497208,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.701200008392334},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.6643999814987183},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.6389999985694885},{"id":"https://openalex.org/keywords/policy-learning","display_name":"Policy learning","score":0.5346999764442444},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.47609999775886536},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.423799991607666}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7107999920845032},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.701200008392334},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.6643999814987183},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.6389999985694885},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.586899995803833},{"id":"https://openalex.org/C2779436431","wikidata":"https://www.wikidata.org/wiki/Q30672407","display_name":"Policy learning","level":2,"score":0.5346999764442444},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.47609999775886536},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.423799991607666},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4140999913215637},{"id":"https://openalex.org/C159877910","wikidata":"https://www.wikidata.org/wiki/Q2202883","display_name":"Autoregressive model","level":2,"score":0.36730000376701355},{"id":"https://openalex.org/C66322947","wikidata":"https://www.wikidata.org/wiki/Q11658","display_name":"Transformer","level":3,"score":0.36480000615119934},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.35499998927116394},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.35269999504089355},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.27390000224113464},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.25780001282691956}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2503.04074","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.04074","pdf_url":"https://arxiv.org/pdf/2503.04074","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.2503.04074","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2503.04074","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:2503.04074","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2503.04074","pdf_url":"https://arxiv.org/pdf/2503.04074","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":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Learning":[0,15],"the":[1,10,18,36,48,57,67,70,75,101,121,131,139],"optimal":[2],"policy":[3,26,49,71,92,102,135,142],"from":[4],"a":[5,30],"random":[6],"network":[7,27,60,93,143],"initialization":[8],"is":[9,127],"theme":[11],"of":[12,20,59,62,69,77,134,141],"deep":[13,53],"Reinforcement":[14],"(RL).":[16],"As":[17],"scale":[19],"DRL":[21,25],"training":[22,110],"increases,":[23],"treating":[24],"weights":[28,61,94],"as":[29,85],"new":[31],"data":[32,105],"modality":[33],"and":[34,40,137],"exploring":[35],"potential":[37],"becomes":[38],"appealing":[39],"possible.":[41],"In":[42,120],"this":[43],"work,":[44],"we":[45,82,114,123],"focus":[46],"on":[47],"learning":[50,72,103,136],"path":[51,104],"in":[52,95],"RL,":[54],"represented":[55],"by":[56,106,144],"trajectory":[58,78],"historical":[63],"policies,":[64],"which":[65,90,113],"reflects":[66],"evolvement":[68],"process.":[73],"Taking":[74],"idea":[76],"modeling":[79],"with":[80,112],"Transformer,":[81],"propose":[83],"Transformer":[84],"Implicit":[86],"Policy":[87],"Learner":[88],"(TIPL),":[89],"processes":[91],"an":[96],"autoregressive":[97],"manner.":[98],"We":[99],"collect":[100],"running":[107],"independent":[108],"RL":[109],"trials,":[111],"then":[115],"train":[116],"our":[117],"TIPL":[118,126],"model.":[119],"experiments,":[122],"demonstrate":[124],"that":[125],"able":[128],"to":[129],"fit":[130],"implicit":[132],"dynamics":[133],"perform":[138],"optimization":[140],"inference.":[145]},"counts_by_year":[],"updated_date":"2026-07-28T07:46:37.118299","created_date":"2025-10-10T00:00:00"}