{"id":"https://openalex.org/W4376864530","doi":"https://doi.org/10.48550/arxiv.2305.05666","title":"Policy Gradient Methods in the Presence of Symmetries and State Abstractions","display_name":"Policy Gradient Methods in the Presence of Symmetries and State Abstractions","publication_year":2023,"publication_date":"2023-05-09","ids":{"openalex":"https://openalex.org/W4376864530","doi":"https://doi.org/10.48550/arxiv.2305.05666"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2305.05666","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.05666","pdf_url":"https://arxiv.org/pdf/2305.05666","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,"listed_in":[],"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"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2305.05666","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068822568","display_name":"Prakash Panangaden","orcid":"https://orcid.org/0000-0001-8763-6172","observed_orcids":["https://orcid.org/0000-0001-8763-6172"]},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]},{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Panangaden, Prakash","raw_affiliation_strings":["School of Computer Science , McGill University and Mila -Quebec AI Institute Montreal , QC , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , McGill University and Mila -Quebec AI Institute Montreal , QC , Canada","institution_ids":["https://openalex.org/I4210164802","https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063455580","display_name":"Sahand Rezaei-Shoshtari","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]},{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Rezaei-Shoshtari, Sahand","raw_affiliation_strings":["School of Computer Science , McGill University and Mila -Quebec AI Institute Montreal , QC , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , McGill University and Mila -Quebec AI Institute Montreal , QC , Canada","institution_ids":["https://openalex.org/I4210164802","https://openalex.org/I5023651"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088011506","display_name":"Rosie Zhao","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I136199984","display_name":"Harvard University","ror":"https://ror.org/03vek6s52","country_code":"US","type":"education","lineage":["https://openalex.org/I136199984"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhao, Rosie","raw_affiliation_strings":["School of Engineering and Applied Sciences Harvard University Cambridge , MA , USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Engineering and Applied Sciences Harvard University Cambridge , MA , USA","institution_ids":["https://openalex.org/I136199984"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109496264","display_name":"David Meger","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]},{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Meger, David","raw_affiliation_strings":["School of Computer Science , McGill University and Mila -Quebec AI Institute Montreal , QC , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , McGill University and Mila -Quebec AI Institute Montreal , QC , Canada","institution_ids":["https://openalex.org/I4210164802","https://openalex.org/I5023651"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065836447","display_name":"Doina Precup","orcid":"https://orcid.org/0000-0003-4718-9851","observed_orcids":["https://orcid.org/0000-0003-4718-9851"]},"institutions":[{"id":"https://openalex.org/I4210164802","display_name":"Mila - Quebec Artificial Intelligence Institute","ror":"https://ror.org/05c22rx21","country_code":"CA","type":"facility","lineage":["https://openalex.org/I4210164802"]},{"id":"https://openalex.org/I5023651","display_name":"McGill University","ror":"https://ror.org/01pxwe438","country_code":"CA","type":"education","lineage":["https://openalex.org/I5023651"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Precup, Doina","raw_affiliation_strings":["School of Computer Science , McGill University and Mila -Quebec AI Institute and DeepMind Montreal , QC , Canada"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computer Science , McGill University and Mila -Quebec AI Institute and DeepMind Montreal , QC , Canada","institution_ids":["https://openalex.org/I4210164802","https://openalex.org/I5023651"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":2,"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":1.0,"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":1.0,"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/T12794","display_name":"Adaptive Dynamic Programming Control","score":0.0,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.0,"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/policy-gradient-theorem","display_name":"policy gradient theorem","score":0.8579999804496765},{"id":"https://openalex.org/keywords/state-abstraction","display_name":"state abstraction","score":0.7889999747276306},{"id":"https://openalex.org/keywords/continuous-symmetries","display_name":"continuous symmetries","score":0.734000027179718},{"id":"https://openalex.org/keywords/action-abstraction","display_name":"action abstraction","score":0.7149999737739563},{"id":"https://openalex.org/keywords/actor-critic-algorithms","display_name":"actor-critic algorithms","score":0.753000020980835},{"id":"https://openalex.org/keywords/representation-learning","display_name":"representation learning","score":0.7369999885559082},{"id":"https://openalex.org/keywords/continuous-control","display_name":"continuous control","score":0.8320000171661377},{"id":"https://openalex.org/keywords/visual-control","display_name":"visual control","score":0.503000020980835},{"id":"https://openalex.org/keywords/deepmind-control-suite","display_name":"DeepMind Control Suite","score":0.9139999747276306}],"concepts":[{"id":"https://openalex.org/C124304363","wikidata":"https://www.wikidata.org/wiki/Q673661","display_name":"Abstraction","level":2,"score":0.707784116268158},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6780736446380615},{"id":"https://openalex.org/C106189395","wikidata":"https://www.wikidata.org/wiki/Q176789","display_name":"Markov decision process","level":3,"score":0.6298822164535522},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.601502537727356},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.557429850101471},{"id":"https://openalex.org/C4042151","wikidata":"https://www.wikidata.org/wiki/Q215111","display_name":"Homomorphism","level":2,"score":0.533660888671875},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.47962841391563416},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4635879695415497},{"id":"https://openalex.org/C198043062","wikidata":"https://www.wikidata.org/wiki/Q180953","display_name":"Metric space","level":2,"score":0.42598438262939453},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.41801419854164124},{"id":"https://openalex.org/C31170391","wikidata":"https://www.wikidata.org/wiki/Q188619","display_name":"Hierarchy","level":2,"score":0.41072767972946167},{"id":"https://openalex.org/C159886148","wikidata":"https://www.wikidata.org/wiki/Q176645","display_name":"Markov process","level":2,"score":0.350588321685791},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3285757303237915},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21373257040977478},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.1112903356552124},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","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/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C34447519","wikidata":"https://www.wikidata.org/wiki/Q179522","display_name":"Market economy","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/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2305.05666","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.05666","pdf_url":"https://arxiv.org/pdf/2305.05666","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,"listed_in":[],"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.2305.05666","doi":"https://doi.org/10.48550/arxiv.2305.05666","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2305.05666","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,"listed_in":[],"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":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2305.05666","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2305.05666","pdf_url":"https://arxiv.org/pdf/2305.05666","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,"listed_in":[],"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":[],"study_designs":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320331257","display_name":"Alliance de recherche num\u00e9rique du Canada","ror":"https://ror.org/010r6td27"},{"id":"https://openalex.org/F4320334593","display_name":"Natural Sciences and Engineering Research Council of Canada","ror":"https://ror.org/01h531d29"}],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4376864530.pdf","grobid_xml":"https://content.openalex.org/works/W4376864530.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W7133205079","https://openalex.org/W7027669051","https://openalex.org/W2902272628","https://openalex.org/W273478400","https://openalex.org/W4285102525","https://openalex.org/W1564393562","https://openalex.org/W7115037791","https://openalex.org/W2166618252","https://openalex.org/W2899685447","https://openalex.org/W4296414154"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,164],"(RL)":[2],"on":[3,9,51,77,139,145],"high-dimensional":[4],"and":[5,14,26,42,58,94,169],"complex":[6],"problems":[7],"relies":[8],"abstraction":[10,21,125],"for":[11,55,66,73,123,162],"improved":[12,167],"efficiency":[13],"generalization.":[15],"In":[16],"this":[17],"paper,":[18],"we":[19,80,106],"study":[20],"in":[22,126],"the":[23,28,37,52,71,92,95,101,118,127,134,151,170,173,178,181],"continuous-control":[24],"setting,":[25],"extend":[27],"definition":[29],"of":[30,39,70,84,110,120,129,136,172,180],"Markov":[31],"decision":[32],"process":[33],"(MDP)":[34],"homomorphisms":[35,161],"to":[36,90,115,158,166],"setting":[38],"continuous":[40,113],"state":[41],"action":[43,124],"spaces.":[44],"We":[45,132],"derive":[46],"a":[47,82,108],"policy":[48,62,74,93],"gradient":[49,63],"theorem":[50],"abstract":[53],"MDP":[54,96,160],"both":[56],"stochastic":[57],"deterministic":[59],"policies.":[60],"Our":[61,155],"results":[64],"allow":[65],"leveraging":[67],"approximate":[68],"symmetries":[69,114],"environment":[72],"optimization.":[75],"Based":[76],"these":[78],"theorems,":[79],"propose":[81],"family":[83],"actor-critic":[85],"algorithms":[86],"that":[87],"are":[88],"able":[89],"learn":[91],"homomorphism":[97],"map":[98],"simultaneously,":[99],"using":[100],"lax":[102],"bisimulation":[103],"metric.":[104],"Finally,":[105],"introduce":[107],"series":[109],"environments":[111],"with":[112],"further":[116],"demonstrate":[117,133,177],"ability":[119,157],"our":[121,137,140],"algorithm":[122],"presence":[128],"such":[130],"symmetries.":[131],"effectiveness":[135],"method":[138],"environments,":[141],"as":[142,144],"well":[143],"challenging":[146],"visual":[147],"control":[148],"tasks":[149],"from":[150],"DeepMind":[152],"Control":[153],"Suite.":[154],"method's":[156],"utilize":[159],"representation":[163],"leads":[165],"performance,":[168],"visualizations":[171],"latent":[174],"space":[175],"clearly":[176],"structure":[179],"learned":[182],"abstraction.":[183]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-10-26T11:51:55.731654","created_date":"2023-05-18T00:00:00"}