{"id":"https://openalex.org/W3035015331","doi":"https://doi.org/10.48550/arxiv.2006.06547","title":"Avoiding Side Effects in Complex Environments","display_name":"Avoiding Side Effects in Complex Environments","publication_year":2020,"publication_date":"2020-06-11","ids":{"openalex":"https://openalex.org/W3035015331","doi":"https://doi.org/10.48550/arxiv.2006.06547","mag":"3035015331"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2006.06547","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.06547","pdf_url":"https://arxiv.org/pdf/2006.06547","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","is_traditional":true,"indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2006.06547","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5024073525","display_name":"Alexander Turner","orcid":"https://orcid.org/0000-0001-7896-3665","observed_orcids":["https://orcid.org/0000-0001-7896-3665"]},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Turner, Alexander Matt","raw_affiliation_strings":["Oregon State University","Oregon State University, Corvallis, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon State University","institution_ids":["https://openalex.org/I131249849"]},{"raw_affiliation_string":"Oregon State University, Corvallis, United States","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076851527","display_name":"Neale Ratzlaff","orcid":null,"observed_orcids":[]},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ratzlaff, Neale","raw_affiliation_strings":["Oregon State University","Oregon State University, Corvallis, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon State University","institution_ids":["https://openalex.org/I131249849"]},{"raw_affiliation_string":"Oregon State University, Corvallis, United States","institution_ids":["https://openalex.org/I131249849"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5014260664","display_name":"Prasad V. Tadepalli","orcid":"https://orcid.org/0000-0003-2736-3912","observed_orcids":["https://orcid.org/0000-0003-2736-3912"]},"institutions":[{"id":"https://openalex.org/I131249849","display_name":"Oregon State University","ror":"https://ror.org/00ysfqy60","country_code":"US","type":"education","lineage":["https://openalex.org/I131249849"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Tadepalli, Prasad","raw_affiliation_strings":["Oregon State University","Oregon State University, Corvallis, United States"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Oregon State University","institution_ids":["https://openalex.org/I131249849"]},{"raw_affiliation_string":"Oregon State University, Corvallis, United States","institution_ids":["https://openalex.org/I131249849"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I131249849"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":19,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"33","issue":null,"first_page":"21406","last_page":"21415"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9824000000953674,"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":0.9824000000953674,"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":0.006200000178068876,"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/T14381","display_name":"Psychiatry, Mental Health, Neuroscience","score":0.00139999995008111,"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/reward-specification","display_name":"reward specification","score":0.8870000243186951},{"id":"https://openalex.org/keywords/conway-s-game-of-life","display_name":"Conway's Game of Life","score":0.8740000128746033},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.42100000381469727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6972835063934326},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.6737784743309021},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.6361226439476013},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.6216754913330078},{"id":"https://openalex.org/C2776760102","wikidata":"https://www.wikidata.org/wiki/Q5139990","display_name":"Code (set theory)","level":3,"score":0.5928597450256348},{"id":"https://openalex.org/C2780565519","wikidata":"https://www.wikidata.org/wiki/Q1208937","display_name":"Multitude","level":2,"score":0.5168507695198059},{"id":"https://openalex.org/C3454156","wikidata":"https://www.wikidata.org/wiki/Q1144241","display_name":"Side effect (computer science)","level":2,"score":0.5117104053497314},{"id":"https://openalex.org/C2776291640","wikidata":"https://www.wikidata.org/wiki/Q2912517","display_name":"Value (mathematics)","level":2,"score":0.4311888515949249},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.1750483512878418},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.12141469120979309},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.10289660096168518},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.09595590829849243},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.07379105687141418},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"pmh:oai:arXiv.org:2006.06547","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.06547","pdf_url":"https://arxiv.org/pdf/2006.06547","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":"mag:3035015331","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/pdf/2006.06547.pdf","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":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"arXiv (Cornell University)","raw_type":null},{"id":"doi:10.48550/arxiv.2006.06547","doi":"https://doi.org/10.48550/arxiv.2006.06547","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2006.06547","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"},{"id":"mag:3104947600","doi":null,"is_oa":false,"landing_page_url":"https://papers.nips.cc/paper/2020/file/f50a6c02a3fc5a3a5d4d9391f05f3efc-Paper.pdf","pdf_url":null,"source":{"id":"https://openalex.org/S4363606243","display_name":"neural information processing systems","issn_l":"1049-5258","issn":["1049-5258"],"is_oa":false,"is_in_doaj":false,"is_core":true,"listed_in":["cwts-core","norway-2"],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":"Neural Information Processing Systems","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2006.06547","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2006.06547","pdf_url":"https://arxiv.org/pdf/2006.06547","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":[{"id":"https://openalex.org/G1037014486","display_name":null,"funder_award_id":"N66001","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G1723748841","display_name":null,"funder_award_id":"N66001-19-2-4035","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G1869269386","display_name":"S&AS: INT: COLLAB: Composable and Verifiable Design for Autonomous Humanoid Robots in Space Missions","funder_award_id":"1724360","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"},{"id":"https://openalex.org/G2284091598","display_name":null,"funder_award_id":"HR001120C0022","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G8215844777","display_name":null,"funder_award_id":"N66001-19","funder_id":"https://openalex.org/F4320332180","funder_display_name":"Defense Advanced Research Projects Agency"},{"id":"https://openalex.org/G822882348","display_name":"RI: Small: Speedup Learning for Online Planning Under Uncertainty","funder_award_id":"1619433","funder_id":"https://openalex.org/F4320306076","funder_display_name":"National Science Foundation"}],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"},{"id":"https://openalex.org/F4320332180","display_name":"Defense Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"},{"id":"https://openalex.org/F4320332815","display_name":"Advanced Research Projects Agency","ror":"https://ror.org/02caytj08"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3035015331.pdf","grobid_xml":"https://content.openalex.org/works/W3035015331.grobid-xml"},"referenced_works_count":26,"referenced_works":["https://openalex.org/W567721252","https://openalex.org/W1518931405","https://openalex.org/W1541317966","https://openalex.org/W1601418373","https://openalex.org/W1845972764","https://openalex.org/W2145339207","https://openalex.org/W2160653514","https://openalex.org/W2288565641","https://openalex.org/W2617069179","https://openalex.org/W2618318883","https://openalex.org/W2626804490","https://openalex.org/W2736601468","https://openalex.org/W2750866482","https://openalex.org/W2768908787","https://openalex.org/W2803543472","https://openalex.org/W2805862167","https://openalex.org/W2808155616","https://openalex.org/W2916350282","https://openalex.org/W2957120403","https://openalex.org/W2962803570","https://openalex.org/W2963780574","https://openalex.org/W2970418800","https://openalex.org/W2979211489","https://openalex.org/W2994180726","https://openalex.org/W2994385233","https://openalex.org/W3034344071"],"related_works":["https://openalex.org/W4386021105","https://openalex.org/W2805862167","https://openalex.org/W3092918135","https://openalex.org/W2994180726","https://openalex.org/W3133010951","https://openalex.org/W4283662528","https://openalex.org/W2921821063","https://openalex.org/W7064023523","https://openalex.org/W3034544796","https://openalex.org/W4280606444"],"abstract_inverted_index":{"Reward":[0],"function":[1],"specification":[2],"can":[3],"be":[4,14],"difficult.":[5],"Rewarding":[6],"the":[7,18,41,80,84],"agent":[8,81],"for":[9,67],"making":[10],"a":[11,68],"widget":[12],"may":[13],"easy,":[15],"but":[16],"penalizing":[17,38],"multitude":[19],"of":[20,61],"possible":[21],"negative":[22],"side":[23,35,90],"effects":[24,36],"is":[25],"hard.":[26],"In":[27],"toy":[28],"environments,":[29],"Attainable":[30],"Utility":[31],"Preservation":[32],"(AUP)":[33],"avoided":[34],"by":[37],"shifts":[39],"in":[40],"ability":[42],"to":[43,52,82],"achieve":[44],"randomly":[45,54,70],"generated":[46,55,71],"goals.":[47],"We":[48],"scale":[49],"this":[50],"approach":[51],"large,":[53],"environments":[56],"based":[57],"on":[58],"Conway's":[59],"Game":[60],"Life.":[62],"By":[63],"preserving":[64],"optimal":[65],"value":[66],"single":[69],"reward":[72],"function,":[73],"AUP":[74],"incurs":[75],"modest":[76],"overhead":[77],"while":[78],"leading":[79],"complete":[83],"specified":[85],"task":[86],"and":[87,93],"avoid":[88],"many":[89],"effects.":[91],"Videos":[92],"code":[94],"are":[95],"available":[96],"at":[97],"https://avoiding-side-effects.github.io/.":[98]},"counts_by_year":[{"year":2026,"cited_by_count":4},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":3},{"year":2022,"cited_by_count":2},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2020-06-19T00:00:00"}
