{"id":"https://openalex.org/W4309183296","doi":"https://doi.org/10.48550/arxiv.2211.05939","title":"pyRDDLGym: From RDDL to Gym Environments","display_name":"pyRDDLGym: From RDDL to Gym Environments","publication_year":2022,"publication_date":"2022-11-11","ids":{"openalex":"https://openalex.org/W4309183296","doi":"https://doi.org/10.48550/arxiv.2211.05939"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2211.05939","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.05939","pdf_url":"https://arxiv.org/pdf/2211.05939","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/2211.05939","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5023063165","display_name":"Ayal Taitler","orcid":"https://orcid.org/0000-0003-3919-6883","observed_orcids":["https://orcid.org/0000-0003-3919-6883"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Taitler, Ayal","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065207769","display_name":"Michael Gimelfarb","orcid":"https://orcid.org/0000-0003-4377-2142","observed_orcids":["https://orcid.org/0000-0003-4377-2142"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gimelfarb, Michael","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Jeong, Jihwan","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jeong, Jihwan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037582330","display_name":"Sriram Gopalakrishnan","orcid":"https://orcid.org/0000-0002-6461-391X","observed_orcids":["https://orcid.org/0000-0002-6461-391X"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Gopalakrishnan, Sriram","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Mladenov, Martin","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mladenov, Martin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":null,"display_name":"Liu, Xiaotian","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Liu, Xiaotian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5028174137","display_name":"Scott Sanner","orcid":"https://orcid.org/0000-0001-7984-8394","observed_orcids":["https://orcid.org/0000-0001-7984-8394"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Sanner, Scott","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"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":0.9990000128746033,"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":0.9990000128746033,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.00039999998989515007,"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/T11574","display_name":"Artificial Intelligence in Games","score":9.999999747378752e-05,"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/openai-gym","display_name":"OpenAI Gym","score":0.9179999828338623},{"id":"https://openalex.org/keywords/environment-generation","display_name":"environment generation","score":0.7120000123977661},{"id":"https://openalex.org/keywords/reinforcement-learning-benchmarks","display_name":"reinforcement learning benchmarks","score":0.7170000076293945},{"id":"https://openalex.org/keywords/conditional-probability-function","display_name":"conditional probability function","score":0.6880000233650208},{"id":"https://openalex.org/keywords/multi-agent-environments","display_name":"multi-agent environments","score":0.6389999985694885},{"id":"https://openalex.org/keywords/model-based-reinforcement-learning","display_name":"model-based reinforcement learning","score":0.7139999866485596}],"concepts":[{"id":"https://openalex.org/C519991488","wikidata":"https://www.wikidata.org/wiki/Q28865","display_name":"Python (programming language)","level":2,"score":0.8186773061752319},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7323604822158813},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.5705979466438293},{"id":"https://openalex.org/C195818886","wikidata":"https://www.wikidata.org/wiki/Q5421724","display_name":"Expressive power","level":2,"score":0.539094090461731},{"id":"https://openalex.org/C99844830","wikidata":"https://www.wikidata.org/wiki/Q102441924","display_name":"Scaling","level":2,"score":0.4776131808757782},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.41988256573677063},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.39670708775520325},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.37442541122436523},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.32934391498565674},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09437614679336548},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2211.05939","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.05939","pdf_url":"https://arxiv.org/pdf/2211.05939","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.2211.05939","doi":"https://doi.org/10.48550/arxiv.2211.05939","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2211.05939","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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2211.05939","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2211.05939","pdf_url":"https://arxiv.org/pdf/2211.05939","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":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3006576697","https://openalex.org/W2757515248","https://openalex.org/W3201903209","https://openalex.org/W3131437315","https://openalex.org/W3211994108","https://openalex.org/W7166291948","https://openalex.org/W4225922064","https://openalex.org/W4387838584","https://openalex.org/W4392974124","https://openalex.org/W4391013162"],"abstract_inverted_index":{"We":[0,70,128],"present":[1,129],"pyRDDLGym,":[2,136],"a":[3,43,64,77],"Python":[4],"framework":[5],"for":[6,120],"auto-generation":[7],"of":[8,21,51,91,99,135],"OpenAI":[9],"Gym":[10,36],"environments":[11,52],"from":[12,122],"RDDL":[13,24,41,110,143],"declerative":[14],"description.":[15],"The":[16],"discrete":[17],"time":[18],"step":[19,37],"evolution":[20],"variables":[22],"in":[23,80,108],"is":[25,42],"described":[26],"by":[27,85],"conditional":[28],"probability":[29],"functions,":[30],"which":[31],"fits":[32],"naturally":[33],"into":[34,148],"the":[35,46,81,95,106,109,130,138,142,149],"scheme.":[38],"Furthermore,":[39],"since":[40],"lifted":[44],"description,":[45,111],"modification":[47],"and":[48,57,88,132,137],"scaling":[49],"up":[50],"to":[53,68,94,105,141],"support":[54],"multiple":[55],"entities":[56],"different":[58],"configurations":[59],"becomes":[60],"trivial":[61],"rather":[62],"than":[63],"tedious":[65],"process":[66],"prone":[67],"errors.":[69],"hope":[71],"that":[72,145],"pyRDDLGym":[73,112],"will":[74],"serve":[75],"as":[76],"new":[78],"wind":[79],"reinforcement":[82],"learning":[83,121],"community":[84],"enabling":[86],"easy":[87],"rapid":[89],"development":[90],"benchmarks":[92],"due":[93],"unique":[96],"expressive":[97],"power":[98],"RDDL.":[100],"By":[101],"providing":[102],"explicit":[103],"access":[104],"model":[107,126],"can":[113],"also":[114],"facilitate":[115],"research":[116],"on":[117],"hybrid":[118],"approaches":[119],"interaction":[123],"while":[124],"leveraging":[125],"knowledge.":[127],"design":[131],"built-in":[133],"examples":[134],"additions":[139],"made":[140],"language":[144],"were":[146],"incorporated":[147],"framework.":[150]},"counts_by_year":[{"year":2024,"cited_by_count":2}],"updated_date":"2026-09-27T08:07:27.782135","created_date":"2022-11-24T00:00:00"}