{"id":"https://openalex.org/W4386755387","doi":"https://doi.org/10.48550/arxiv.2309.06921","title":"Investigating the Impact of Action Representations in Policy Gradient Algorithms","display_name":"Investigating the Impact of Action Representations in Policy Gradient Algorithms","publication_year":2023,"publication_date":"2023-09-13","ids":{"openalex":"https://openalex.org/W4386755387","doi":"https://doi.org/10.48550/arxiv.2309.06921"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2309.06921","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.06921","pdf_url":"https://arxiv.org/pdf/2309.06921","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"},"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2309.06921","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Schneider, Jan","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Schneider, Jan","raw_affiliation_strings":[],"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":[],"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":[],"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":[],"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":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":5,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"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":0.9958999752998352,"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":0.9958999752998352,"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":0.9524000287055969,"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/T10603","display_name":"Smart Grid Energy Management","score":0.921999990940094,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8201700448989868},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.793550968170166},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7291457056999207},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6243411302566528},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6231202483177185},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.6212880611419678},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5536471605300903},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33477017283439636}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8201700448989868},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.793550968170166},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7291457056999207},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6243411302566528},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6231202483177185},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.6212880611419678},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5536471605300903},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33477017283439636},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2309.06921","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.06921","pdf_url":"https://arxiv.org/pdf/2309.06921","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":"doi:10.48550/arxiv.2309.06921","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2309.06921","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":"article"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2309.06921","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2309.06921","pdf_url":"https://arxiv.org/pdf/2309.06921","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"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.6899999976158142}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4386755387.pdf"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2378211422","https://openalex.org/W2745001401","https://openalex.org/W4321353415","https://openalex.org/W2130974462","https://openalex.org/W2028665553","https://openalex.org/W2086519370","https://openalex.org/W972276598","https://openalex.org/W2087343574","https://openalex.org/W4246352526","https://openalex.org/W2121910908"],"abstract_inverted_index":{"Reinforcement":[0],"learning~(RL)":[1],"is":[2],"a":[3],"versatile":[4],"framework":[5],"for":[6,37,94],"learning":[7,17,57],"to":[8,77],"solve":[9],"complex":[10],"real-world":[11],"tasks.":[12,63],"However,":[13],"influences":[14],"on":[15,59],"the":[16,39,50,56,71,80,83],"performance":[18,58,72],"of":[19,41,70,82,91],"RL":[20,61,95],"algorithms":[21],"are":[22],"often":[23],"poorly":[24],"understood":[25],"in":[26,44,79],"practice.":[27],"We":[28],"discuss":[29,88],"different":[30],"analysis":[31,65,92],"techniques":[32,93],"and":[33],"assess":[34],"their":[35],"effectiveness":[36],"investigating":[38],"impact":[40],"action":[42,51],"representations":[43],"RL.":[45],"Our":[46],"experiments":[47],"demonstrate":[48],"that":[49,68],"representation":[52],"can":[53,74],"significantly":[54],"influence":[55],"popular":[60],"benchmark":[62],"The":[64],"results":[66],"indicate":[67],"some":[69],"differences":[73],"be":[75],"attributed":[76],"changes":[78],"complexity":[81],"optimization":[84],"landscape.":[85],"Finally,":[86],"we":[87],"open":[89],"challenges":[90],"algorithms.":[96]},"counts_by_year":[],"updated_date":"2026-04-21T08:09:41.155169","created_date":"2023-09-15T00:00:00"}