{"id":"https://openalex.org/W4385768012","doi":"https://doi.org/10.24963/ijcai.2023/384","title":"Scaling Goal-based Exploration via Pruning Proto-goals","display_name":"Scaling Goal-based Exploration via Pruning Proto-goals","publication_year":2023,"publication_date":"2023-08-01","ids":{"openalex":"https://openalex.org/W4385768012","doi":"https://doi.org/10.24963/ijcai.2023/384"},"language":"en","primary_location":{"id":"doi:10.24963/ijcai.2023/384","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/384","pdf_url":"https://www.ijcai.org/proceedings/2023/0384.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.ijcai.org/proceedings/2023/0384.pdf","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5080105613","display_name":"Akhil Bagaria","orcid":null},"institutions":[{"id":"https://openalex.org/I175594653","display_name":"John Brown University","ror":"https://ror.org/02ct41q97","country_code":"US","type":"education","lineage":["https://openalex.org/I175594653"]},{"id":"https://openalex.org/I27804330","display_name":"Brown University","ror":"https://ror.org/05gq02987","country_code":"US","type":"education","lineage":["https://openalex.org/I27804330"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Akhil Bagaria","raw_affiliation_strings":["Brown University","Brown University, Providence, RI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Brown University","institution_ids":["https://openalex.org/I175594653"]},{"raw_affiliation_string":"Brown University, Providence, RI, USA","institution_ids":["https://openalex.org/I27804330"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081322018","display_name":"Tom Schaul","orcid":"https://orcid.org/0000-0002-2961-8782"},"institutions":[{"id":"https://openalex.org/I4210090411","display_name":"Google DeepMind (United Kingdom)","ror":"https://ror.org/00971b260","country_code":"GB","type":"company","lineage":["https://openalex.org/I4210090411","https://openalex.org/I4210128969"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Tom Schaul","raw_affiliation_strings":["DeepMind","DeepMind, London, UK"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"DeepMind","institution_ids":["https://openalex.org/I4210090411"]},{"raw_affiliation_string":"DeepMind, London, UK","institution_ids":["https://openalex.org/I4210090411"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5080105613"],"corresponding_institution_ids":["https://openalex.org/I175594653","https://openalex.org/I27804330"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"3451","last_page":"3460"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9998000264167786,"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":0.9998000264167786,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.9726999998092651,"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":0.9611999988555908,"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/generality","display_name":"Generality","score":0.8214685916900635},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7524460554122925},{"id":"https://openalex.org/keywords/novelty","display_name":"Novelty","score":0.7482626438140869},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.7048752307891846},{"id":"https://openalex.org/keywords/pruning","display_name":"Pruning","score":0.6824743151664734},{"id":"https://openalex.org/keywords/space","display_name":"Space (punctuation)","score":0.5680735111236572},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.47718632221221924},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.46231967210769653},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.44790032505989075},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.33534616231918335},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.33287307620048523}],"concepts":[{"id":"https://openalex.org/C2780767217","wikidata":"https://www.wikidata.org/wiki/Q5532421","display_name":"Generality","level":2,"score":0.8214685916900635},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7524460554122925},{"id":"https://openalex.org/C2778738651","wikidata":"https://www.wikidata.org/wiki/Q16546687","display_name":"Novelty","level":2,"score":0.7482626438140869},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7048752307891846},{"id":"https://openalex.org/C108010975","wikidata":"https://www.wikidata.org/wiki/Q500094","display_name":"Pruning","level":2,"score":0.6824743151664734},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.5680735111236572},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.47718632221221924},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.46231967210769653},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.44790032505989075},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.33534616231918335},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.33287307620048523},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C6557445","wikidata":"https://www.wikidata.org/wiki/Q173113","display_name":"Agronomy","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/C542102704","wikidata":"https://www.wikidata.org/wiki/Q183257","display_name":"Psychotherapist","level":1,"score":0.0},{"id":"https://openalex.org/C27206212","wikidata":"https://www.wikidata.org/wiki/Q34178","display_name":"Theology","level":1,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.24963/ijcai.2023/384","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/384","pdf_url":"https://www.ijcai.org/proceedings/2023/0384.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.24963/ijcai.2023/384","is_oa":true,"landing_page_url":"http://dx.doi.org/10.24963/ijcai.2023/384","pdf_url":"https://www.ijcai.org/proceedings/2023/0384.pdf","source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","raw_type":"proceedings-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4385768012.pdf"},"referenced_works_count":57,"referenced_works":["https://openalex.org/W567721252","https://openalex.org/W1488730473","https://openalex.org/W1595483645","https://openalex.org/W1863227302","https://openalex.org/W1988526405","https://openalex.org/W2034806191","https://openalex.org/W2108114251","https://openalex.org/W2108535023","https://openalex.org/W2109910161","https://openalex.org/W2112874374","https://openalex.org/W2132301339","https://openalex.org/W2132622533","https://openalex.org/W2139612737","https://openalex.org/W2160589914","https://openalex.org/W2280163991","https://openalex.org/W2556477470","https://openalex.org/W2586680856","https://openalex.org/W2623491082","https://openalex.org/W2724169821","https://openalex.org/W2807588596","https://openalex.org/W2885550588","https://openalex.org/W2908064123","https://openalex.org/W2940545298","https://openalex.org/W2950040888","https://openalex.org/W2950872548","https://openalex.org/W2962730405","https://openalex.org/W2963276097","https://openalex.org/W2963438456","https://openalex.org/W2963523627","https://openalex.org/W2963864421","https://openalex.org/W2964067469","https://openalex.org/W2964227312","https://openalex.org/W2971273232","https://openalex.org/W2972414681","https://openalex.org/W2995636097","https://openalex.org/W3034296891","https://openalex.org/W3034956653","https://openalex.org/W3035717769","https://openalex.org/W3037871539","https://openalex.org/W3098336382","https://openalex.org/W3129322645","https://openalex.org/W3129981047","https://openalex.org/W3167815619","https://openalex.org/W3190864623","https://openalex.org/W3199151886","https://openalex.org/W4214717370","https://openalex.org/W4226500654","https://openalex.org/W4283640713","https://openalex.org/W4285009743","https://openalex.org/W4286959346","https://openalex.org/W4287020206","https://openalex.org/W4293112425","https://openalex.org/W4294786244","https://openalex.org/W4300799055","https://openalex.org/W4301369009","https://openalex.org/W4386484398","https://openalex.org/W4394666657"],"related_works":["https://openalex.org/W2045049461","https://openalex.org/W1978893398","https://openalex.org/W2201908702","https://openalex.org/W4381094582","https://openalex.org/W2369625323","https://openalex.org/W2364579609","https://openalex.org/W1977906818","https://openalex.org/W1522139108","https://openalex.org/W2353528968","https://openalex.org/W1967082116"],"abstract_inverted_index":{"One":[0],"of":[1,90,99],"the":[2,46,63,67,103],"gnarliest":[3],"challenges":[4],"in":[5,41,108],"reinforcement":[6],"learning":[7],"(RL)":[8],"is":[9,44,105],"exploration":[10,101],"that":[11],"scales":[12],"to":[13,28,70,83,86],"vast":[14,73],"domains,":[15],"where":[16],"novelty-,":[17],"or":[18],"coverage-seeking":[19],"behaviour":[20],"falls":[21],"short.":[22],"Goal-directed,":[23],"purposeful":[24],"behaviours":[25],"are":[26],"able":[27],"overcome":[29],"this,":[30],"but":[31,74],"rely":[32],"on":[33],"a":[34,72,87],"good":[35],"goal":[36,42],"space.":[37],"The":[38,97],"core":[39],"challenge":[40],"discovery":[43,81],"finding":[45],"right":[47],"balance":[48],"between":[49],"generality":[50],"(not":[51],"hand-crafted)":[52],"and":[53,78,94],"tractability":[54],"(useful,":[55],"not":[56],"too":[57],"many).":[58],"Our":[59],"approach":[60],"explicitly":[61],"seeks":[62],"middle":[64],"ground,":[65],"enabling":[66],"human":[68],"designer":[69],"specify":[71],"meaningful":[75],"proto-goal":[76],"space,":[77],"an":[79],"autonomous":[80],"process":[82],"refine":[84],"this":[85],"narrower":[88],"space":[89],"controllable,":[91],"reachable,":[92],"novel,":[93],"relevant":[95],"goals.":[96],"effectiveness":[98],"goal-conditioned":[100],"with":[102],"latter":[104],"then":[106],"demonstrated":[107],"three":[109],"challenging":[110],"environments.":[111]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}