{"id":"https://openalex.org/W3191607011","doi":"https://doi.org/10.1007/978-3-030-83906-2_18","title":"No Free Lunch: Overcoming Reward Gaming in AI Safety Gridworlds","display_name":"No Free Lunch: Overcoming Reward Gaming in AI Safety Gridworlds","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3191607011","doi":"https://doi.org/10.1007/978-3-030-83906-2_18","mag":"3191607011"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-030-83906-2_18","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-83906-2_18","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"book-chapter","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.manchester.ac.uk/en/publications/be209d35-10c7-4c87-8cdc-9e1551c860a9","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5082182773","display_name":"Mariya Tsvarkaleva","orcid":"https://orcid.org/0000-0003-4843-6818"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"Mariya Tsvarkaleva","raw_affiliation_strings":["Department of Computer Science, The University of Manchester, Manchester, UK"],"raw_orcid":"https://orcid.org/0000-0003-4843-6818","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040721287","display_name":"Louise A. Dennis","orcid":"https://orcid.org/0000-0003-1426-1896"},"institutions":[{"id":"https://openalex.org/I28407311","display_name":"University of Manchester","ror":"https://ror.org/027m9bs27","country_code":"GB","type":"education","lineage":["https://openalex.org/I28407311"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Louise A. Dennis","raw_affiliation_strings":["Department of Computer Science, The University of Manchester, Manchester, UK"],"raw_orcid":"https://orcid.org/0000-0003-1426-1896","affiliations":[{"raw_affiliation_string":"Department of Computer Science, The University of Manchester, Manchester, UK","institution_ids":["https://openalex.org/I28407311"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5082182773"],"corresponding_institution_ids":["https://openalex.org/I28407311"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":0.359,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.57553366,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"226","last_page":"238"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9988999962806702,"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":0.9988999962806702,"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":0.9941999912261963,"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/T11975","display_name":"Evolutionary Algorithms and Applications","score":0.989300012588501,"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/heuristics","display_name":"Heuristics","score":0.8325064778327942},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.799420952796936},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7415188550949097},{"id":"https://openalex.org/keywords/heuristic","display_name":"Heuristic","score":0.730114221572876},{"id":"https://openalex.org/keywords/suite","display_name":"Suite","score":0.7162865996360779},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.602933406829834},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5286797881126404},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.46291616559028625},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3686409592628479},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.32303380966186523}],"concepts":[{"id":"https://openalex.org/C127705205","wikidata":"https://www.wikidata.org/wiki/Q5748245","display_name":"Heuristics","level":2,"score":0.8325064778327942},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.799420952796936},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7415188550949097},{"id":"https://openalex.org/C173801870","wikidata":"https://www.wikidata.org/wiki/Q201413","display_name":"Heuristic","level":2,"score":0.730114221572876},{"id":"https://openalex.org/C79581498","wikidata":"https://www.wikidata.org/wiki/Q1367530","display_name":"Suite","level":2,"score":0.7162865996360779},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.602933406829834},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5286797881126404},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.46291616559028625},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3686409592628479},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.32303380966186523},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C166957645","wikidata":"https://www.wikidata.org/wiki/Q23498","display_name":"Archaeology","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0},{"id":"https://openalex.org/C95457728","wikidata":"https://www.wikidata.org/wiki/Q309","display_name":"History","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/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/978-3-030-83906-2_18","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-030-83906-2_18","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:pure.atira.dk:openaire/be209d35-10c7-4c87-8cdc-9e1551c860a9","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/be209d35-10c7-4c87-8cdc-9e1551c860a9","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Tsvarkaleva, M & Dennis, L 2021, No Free Lunch: Overcoming Reward Gaming in AI Safety Gridworlds. in 4th International Workshop on Artificial Intelligence Safety Engineering (WAISE 2021) . vol. 12853. https://doi.org/10.1007/978-3-030-83906-2_18","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:pure.atira.dk:publications/be209d35-10c7-4c87-8cdc-9e1551c860a9","is_oa":true,"landing_page_url":"https://www.research.manchester.ac.uk/portal/en/publications/no-free-lunch-overcoming-reward-gaming-in-ai-safety-gridworlds(be209d35-10c7-4c87-8cdc-9e1551c860a9).html","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Tsvarkaleva, M & Dennis, L 2021, No Free Lunch: Overcoming Reward Gaming in AI Safety Gridworlds. in 4th International Workshop on Artificial Intelligence Safety Engineering (WAISE 2021) . vol. 12853. https://doi.org/10.1007/978-3-030-83906-2_18","raw_type":"info:eu-repo/semantics/publishedVersion"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:openaire/be209d35-10c7-4c87-8cdc-9e1551c860a9","is_oa":true,"landing_page_url":"https://research.manchester.ac.uk/en/publications/be209d35-10c7-4c87-8cdc-9e1551c860a9","pdf_url":null,"source":{"id":"https://openalex.org/S4306400662","display_name":"Research Explorer (The University of Manchester)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I28407311","host_organization_name":"University of Manchester","host_organization_lineage":["https://openalex.org/I28407311"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Tsvarkaleva, M & Dennis, L 2021, No Free Lunch: Overcoming Reward Gaming in AI Safety Gridworlds. in 4th International Workshop on Artificial Intelligence Safety Engineering (WAISE 2021) . vol. 12853. https://doi.org/10.1007/978-3-030-83906-2_18","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W41554520","https://openalex.org/W1757796397","https://openalex.org/W2121863487","https://openalex.org/W2257979135","https://openalex.org/W2617191410","https://openalex.org/W2750866482","https://openalex.org/W2761873684","https://openalex.org/W2768908787","https://openalex.org/W2805862167","https://openalex.org/W2902907165","https://openalex.org/W2963327353","https://openalex.org/W6638754659","https://openalex.org/W6741089554"],"related_works":["https://openalex.org/W3177062893","https://openalex.org/W3125143773","https://openalex.org/W2007032764","https://openalex.org/W803550684","https://openalex.org/W2483226803","https://openalex.org/W4352977312","https://openalex.org/W4312926500","https://openalex.org/W2067280619","https://openalex.org/W4251343851","https://openalex.org/W2041180560"],"abstract_inverted_index":null,"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
