{"id":"https://openalex.org/W433090113","doi":null,"title":"Information-driven intrinsic motivation in reinforcement learning","display_name":"Information-driven intrinsic motivation in reinforcement learning","publication_year":2013,"publication_date":"2013-06-25","ids":{"openalex":"https://openalex.org/W433090113","mag":"433090113"},"language":"en","primary_location":{"id":"mag:433090113","doi":null,"is_oa":false,"landing_page_url":"https://www.mis.mpg.de/preprints/2013/preprint2013_60.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null},"volume":null,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5058348013","display_name":"Keyan Ghazi-Zahedi","orcid":"https://orcid.org/0000-0003-0409-6284","observed_orcids":["https://orcid.org/0000-0003-0409-6284"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Keyan Ghazi-Zahedi","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-0409-6284","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5001474340","display_name":"Georg Martius","orcid":"https://orcid.org/0000-0002-8963-7627","observed_orcids":["https://orcid.org/0000-0002-8963-7627"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Georg Martius","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-8963-7627","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5065926474","display_name":"Nihat Ay","orcid":"https://orcid.org/0000-0002-8527-2579","observed_orcids":["https://orcid.org/0000-0002-8527-2579"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Nihat Ay","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-8527-2579","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.0,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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":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/T11883","display_name":"Embodied and Extended Cognition","score":0.0,"subfield":{"id":"https://openalex.org/subfields/2805","display_name":"Cognitive Neuroscience"},"field":{"id":"https://openalex.org/fields/28","display_name":"Neuroscience"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T14381","display_name":"Psychiatry, Mental Health, Neuroscience","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/intrinsic-motivation","display_name":"intrinsic motivation","score":0.8889999985694885},{"id":"https://openalex.org/keywords/predictive-information","display_name":"predictive information","score":0.9879999756813049},{"id":"https://openalex.org/keywords/mutual-information","display_name":"mutual information","score":0.8299999833106995},{"id":"https://openalex.org/keywords/embodied-ai","display_name":"embodied AI","score":0.7160000205039978},{"id":"https://openalex.org/keywords/open-ended-learning","display_name":"open-ended learning","score":0.8619999885559082},{"id":"https://openalex.org/keywords/exploration","display_name":"exploration","score":0.5699999928474426},{"id":"https://openalex.org/keywords/policy-gradient","display_name":"policy gradient","score":0.5410000085830688},{"id":"https://openalex.org/keywords/extrinsic-rewards","display_name":"extrinsic rewards","score":0.503000020980835}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7690340280532837},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7595547437667847},{"id":"https://openalex.org/C100609095","wikidata":"https://www.wikidata.org/wiki/Q1335050","display_name":"Embodied cognition","level":2,"score":0.6100966334342957},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5932657718658447},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5761120915412903},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.533112645149231},{"id":"https://openalex.org/C2985564149","wikidata":"https://www.wikidata.org/wiki/Q644302","display_name":"Intrinsic motivation","level":2,"score":0.48766887187957764},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.36069661378860474},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.2859855890274048},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.15901732444763184},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.13420331478118896},{"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/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","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":1,"locations":[{"id":"mag:433090113","doi":null,"is_oa":false,"landing_page_url":"https://www.mis.mpg.de/preprints/2013/preprint2013_60.pdf","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W172298727","https://openalex.org/W961347149","https://openalex.org/W1486707268","https://openalex.org/W1550989509","https://openalex.org/W1558521349","https://openalex.org/W1569114984","https://openalex.org/W1583833196","https://openalex.org/W1652032257","https://openalex.org/W1863227302","https://openalex.org/W1977308918","https://openalex.org/W1984324457","https://openalex.org/W1994101655","https://openalex.org/W1999151641","https://openalex.org/W2035788321","https://openalex.org/W2036613247","https://openalex.org/W2043615441","https://openalex.org/W2060841334","https://openalex.org/W2061868368","https://openalex.org/W2065264265","https://openalex.org/W2072492557","https://openalex.org/W2074499097","https://openalex.org/W2075694080","https://openalex.org/W2078150668","https://openalex.org/W2090252028","https://openalex.org/W2101524054","https://openalex.org/W2112874374","https://openalex.org/W2113501460","https://openalex.org/W2121863487","https://openalex.org/W2122798561","https://openalex.org/W2128957129","https://openalex.org/W2137104525","https://openalex.org/W2145556256","https://openalex.org/W2326837301","https://openalex.org/W2341171179","https://openalex.org/W2481414473","https://openalex.org/W3105114223"],"related_works":["https://openalex.org/W2124035349","https://openalex.org/W4384944496","https://openalex.org/W7020075990","https://openalex.org/W2065264265","https://openalex.org/W3128190331","https://openalex.org/W2039862345","https://openalex.org/W2412288866","https://openalex.org/W3045514431","https://openalex.org/W2074499097","https://openalex.org/W3099621306"],"abstract_inverted_index":{"One":[0],"of":[1,8,17,51,56,68,89,95,102,141,173],"the":[2,6,13,45,52,57,76,96,135,138,142,171],"main":[3],"challenges":[4],"in":[5,41,118,154],"eld":[7],"embodied":[9],"articial":[10],"intelligence":[11],"is":[12,22,37,80,110,150],"open-ended":[14,87],"autonomous":[15],"learning":[16,88],"complex":[18,90],"behaviours.":[19],"Our":[20],"approach":[21],"to":[23,29,84,99,120,134],"use":[24],"task-independent,":[25],"information-driven":[26],"intrinsic":[27,62],"motivation(s)":[28],"support":[30,85],"task-dependent":[31],"learning.":[32],"The":[33,108],"work":[34],"presented":[35,129],"here":[36],"a":[38,81,93,164],"preliminary":[39],"step":[40],"which":[42],"we":[43],"investigate":[44],"predictive":[46,77],"information":[47,50,78],"(the":[48],"mutual":[49],"past":[53],"and":[54,104,130],"future":[55],"sensor":[58],"stream)":[59],"as":[60],"an":[61,100,146,155,174],"drive,":[63],"ideally":[64],"supporting":[65],"any":[66,122],"kind":[67],"task":[69],"acquisition.":[70],"Previous":[71],"experiments":[72,127],"have":[73],"shown":[74],"that":[75,111,137],"(PI)":[79],"good":[82],"candidate":[83],"autonomous,":[86],"behaviours,":[91],"because":[92],"maximisation":[94],"PI":[97,144],"corresponds":[98],"exploration":[101],"morphology-":[103],"environment-dependent":[105],"behavioural":[106],"regularities.":[107],"idea":[109],"these":[112],"regularities":[113],"can":[114,167],"then":[115],"be":[116,168],"exploited":[117],"order":[119],"solve":[121],"given":[123],"task.":[124],"Three":[125],"dierent":[126],"are":[128],"their":[131],"results":[132],"lead":[133],"conclusion":[136],"linear":[139],"combination":[140],"one-step":[143],"with":[145],"external":[147],"reward":[148],"function":[149],"not":[151],"generally":[152],"recommended":[153],"episodic":[156],"policy":[157],"gradient":[158],"setting.":[159],"Only":[160],"for":[161],"hard":[162],"tasks":[163],"great":[165],"speed-up":[166],"achieved":[169],"at":[170],"cost":[172],"asymptotic":[175],"performance":[176],"lost.":[177]},"counts_by_year":[],"updated_date":"2026-11-04T10:54:05.112534","created_date":"2016-06-24T00:00:00"}