{"id":"https://openalex.org/W7064023523","doi":null,"title":"Analyzing Approaches to the Problem of Avoiding Side Effects in Autonomous Agents","display_name":"Analyzing Approaches to the Problem of Avoiding Side Effects in Autonomous Agents","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W7064023523"},"language":"en","primary_location":{"id":"pmh:oai:www.duo.uio.no:10852/79594","doi":null,"is_oa":true,"landing_page_url":"http://urn.nb.no/URN:NBN:no-82785","pdf_url":"http://hdl.handle.net/10852/79594","source":{"id":"https://openalex.org/S7407064446","display_name":"NORA - Norwegian Open Research Archives","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/masterThesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://hdl.handle.net/10852/79594","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Waisi, Serwa","orcid":null,"observed_orcids":[]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Waisi, Serwa","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":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":true,"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/T10906","display_name":"AI-based Problem Solving and Planning","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"}},{"id":"https://openalex.org/T10883","display_name":"Ethics and Social Impacts of AI","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/reinforcement-learning","display_name":"reinforcement learning","score":0.7829999923706055},{"id":"https://openalex.org/keywords/adverse-effects","display_name":"adverse effects","score":0.671999990940094},{"id":"https://openalex.org/keywords/autonomous-agents","display_name":"autonomous agents","score":0.8960000276565552},{"id":"https://openalex.org/keywords/safety","display_name":"safety","score":0.6610000133514404},{"id":"https://openalex.org/keywords/reward-shaping","display_name":"reward shaping","score":0.6340000033378601},{"id":"https://openalex.org/keywords/agent-environment-interaction","display_name":"agent-environment interaction","score":0.5450000166893005}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7009000182151794},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6191999912261963},{"id":"https://openalex.org/C2777363581","wikidata":"https://www.wikidata.org/wiki/Q15098235","display_name":"Harm","level":2,"score":0.6191999912261963},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5224000215530396},{"id":"https://openalex.org/C148220186","wikidata":"https://www.wikidata.org/wiki/Q7111912","display_name":"Outcome (game theory)","level":2,"score":0.4844000041484833},{"id":"https://openalex.org/C112930515","wikidata":"https://www.wikidata.org/wiki/Q4389547","display_name":"Risk analysis (engineering)","level":1,"score":0.47909998893737793},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.46970000863075256},{"id":"https://openalex.org/C13687954","wikidata":"https://www.wikidata.org/wiki/Q4826847","display_name":"Autonomous agent","level":2,"score":0.4620000123977661},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3910999894142151},{"id":"https://openalex.org/C41550386","wikidata":"https://www.wikidata.org/wiki/Q529909","display_name":"Multi-agent system","level":2,"score":0.3619000017642975},{"id":"https://openalex.org/C2776654903","wikidata":"https://www.wikidata.org/wiki/Q2601463","display_name":"SAFER","level":2,"score":0.35899999737739563},{"id":"https://openalex.org/C9652623","wikidata":"https://www.wikidata.org/wiki/Q190109","display_name":"Field (mathematics)","level":2,"score":0.3407000005245209},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.3278000056743622},{"id":"https://openalex.org/C2776544517","wikidata":"https://www.wikidata.org/wiki/Q189447","display_name":"Unexpected events","level":2,"score":0.32670000195503235},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.31610000133514404},{"id":"https://openalex.org/C18762648","wikidata":"https://www.wikidata.org/wiki/Q42213","display_name":"Work (physics)","level":2,"score":0.2953000068664551},{"id":"https://openalex.org/C74072328","wikidata":"https://www.wikidata.org/wiki/Q1142726","display_name":"Intelligent agent","level":2,"score":0.27889999747276306},{"id":"https://openalex.org/C3454156","wikidata":"https://www.wikidata.org/wiki/Q1144241","display_name":"Side effect (computer science)","level":2,"score":0.2775999903678894},{"id":"https://openalex.org/C190839683","wikidata":"https://www.wikidata.org/wiki/Q2448197","display_name":"Train","level":2,"score":0.27649998664855957},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C182306322","wikidata":"https://www.wikidata.org/wiki/Q1779371","display_name":"Order (exchange)","level":2,"score":0.26179999113082886},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.2578999996185303}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:www.duo.uio.no:10852/79594","doi":null,"is_oa":true,"landing_page_url":"http://urn.nb.no/URN:NBN:no-82785","pdf_url":"http://hdl.handle.net/10852/79594","source":{"id":"https://openalex.org/S7407064446","display_name":"NORA - Norwegian Open Research Archives","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/masterThesis"}],"best_oa_location":{"id":"pmh:oai:www.duo.uio.no:10852/79594","doi":null,"is_oa":true,"landing_page_url":"http://urn.nb.no/URN:NBN:no-82785","pdf_url":"http://hdl.handle.net/10852/79594","source":{"id":"https://openalex.org/S7407064446","display_name":"NORA - Norwegian Open Research Archives","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"info:eu-repo/semantics/masterThesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7064023523.pdf","grobid_xml":"https://content.openalex.org/works/W7064023523.grobid-xml"},"referenced_works_count":3,"referenced_works":["https://openalex.org/W2462906003","https://openalex.org/W3037207827","https://openalex.org/W4211086838"],"related_works":["https://openalex.org/W3092156675","https://openalex.org/W2994180726","https://openalex.org/W2805862167","https://openalex.org/W2921821063","https://openalex.org/W7124317441","https://openalex.org/W4280606444","https://openalex.org/W6987012538","https://openalex.org/W4398192226","https://openalex.org/W4385327555","https://openalex.org/W7015655229"],"abstract_inverted_index":{"Reinforcement":[0],"learning":[1,7,20,253],"is":[2,50,105,151,197,210,226,250],"a":[3,141,166,182,188,212],"field":[4],"within":[5],"machine":[6],"which":[8,56],"trains":[9],"agents":[10],"to":[11,51,80,106,109,139,153,252,271],"solve":[12,272],"problems":[13],"by":[14],"trial":[15],"and":[16,83,114,185,229,249,269],"error.":[17],"A":[18],"reinforcement":[19],"agent":[21,36,49,66,138,192,221,242,259],"interacts":[22],"with":[23],"the":[24,30,35,47,59,65,81,86,125,137,194,202,218,220,223,231,241,244,254,258,261,273],"environment":[25,82],"through":[26],"actions.":[27],"Depending":[28],"on":[29],"outcome":[31],"of":[32,46,62,144,201,214,233,275],"these":[33],"actions,":[34],"can":[37,73],"either":[38],"be":[39],"rewarded":[40],"or":[41,77,162],"penalized.":[42],"The":[43,100,170,191,236],"overall":[44],"goal":[45],"autonomous":[48],"maximize":[52],"its":[53,68,71,215],"objective":[54,69,127],"function,":[55,70],"means":[57],"obtaining":[58],"maximum":[60],"amount":[61],"rewards.":[63],"While":[64],"follows":[67],"action":[72],"cause":[74,159],"unexpected":[75,160],"harm":[76,161],"unwanted":[78,89,163],"changes":[79,164],"thus":[84],"breach":[85],"safety.":[87],"These":[88,129],"events":[90],"that":[91,157,240],"might":[92],"occur":[93],"are":[94,131],"defined":[95],"as":[96,149,208,267],"negative":[97,111],"side":[98,112,146,206,276],"effects.":[99,277],"focus":[101],"in":[102,124,165,177,181,187,193,222,243,260],"this":[103,118],"work":[104],"analyze":[107],"approaches":[108],"avoid":[110],"effects":[113,147],"find":[115],"solutions":[116],"for":[117,204],"problem,":[119],"without":[120],"integrating":[121],"ad-hoc":[122],"constraints":[123,130],"agent's":[126],"function.":[128],"not":[132,198,211,265],"integrated":[133],"since":[134],"we":[135],"want":[136],"have":[140],"general":[142],"knowledge":[143],"solving":[145],"problems,":[148],"it":[150,209],"impossible":[152],"foresee":[154],"all":[155],"actions":[156],"could":[158],"real":[167],"world":[168],"environment.":[169],"experimental":[171,237],"part":[172,213,238],"compares":[173],"two":[174],"environments":[175],"implemented":[176],"different":[178],"settings,":[179],"one":[180,186],"safety":[183,195,262],"setting":[184,196,225,246,263],"standard":[189,224,245],"setting.":[190],"directly":[199,227],"aware":[200],"penalization":[203],"causing":[205,234],"effects,":[207],"objective.":[216],"On":[217],"contrary,":[219],"penalized":[228],"knows":[230],"consequence":[232],"harm.":[235],"shows":[239],"performs":[247],"well":[248],"close":[251],"optimal":[255],"behaviour.":[256],"Meanwhile,":[257],"does":[264],"behave":[266],"desired":[268],"fails":[270],"problem":[274]},"counts_by_year":[],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2025-10-10T00:00:00"}