{"id":"https://openalex.org/W3163453895","doi":"https://doi.org/10.5220/0010640200003063","title":"Reward Prediction for Representation Learning and Reward Shaping","display_name":"Reward Prediction for Representation Learning and Reward Shaping","publication_year":2021,"publication_date":"2021-01-01","ids":{"openalex":"https://openalex.org/W3163453895","doi":"https://doi.org/10.5220/0010640200003063","mag":"3163453895"},"language":"en","primary_location":{"id":"doi:10.5220/0010640200003063","is_oa":false,"landing_page_url":"https://doi.org/10.5220/0010640200003063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Joint Conference on Computational Intelligence","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["arxiv","crossref","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2105.03172","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5084714383","display_name":"Hlynur Dav\u00ed\u00f0 Hlynsson","orcid":"https://orcid.org/0000-0002-9487-8054"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Hlynur Dav\u00ed\u00f0 Hlynsson","raw_affiliation_strings":["Institut f\u00fcr Neuroinformatik, Ruhr-Universit\u00e4t Bochum, Universit\u00e4tsstra\u00dfe 150, Bochum, Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Neuroinformatik, Ruhr-Universit\u00e4t Bochum, Universit\u00e4tsstra\u00dfe 150, Bochum, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I904495901"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5039663126","display_name":"Laurenz Wiskott","orcid":"https://orcid.org/0000-0001-6237-740X"},"institutions":[{"id":"https://openalex.org/I904495901","display_name":"Ruhr University Bochum","ror":"https://ror.org/04tsk2644","country_code":"DE","type":"education","lineage":["https://openalex.org/I904495901"]}],"countries":["DE"],"is_corresponding":false,"raw_author_name":"Laurenz Wiskott","raw_affiliation_strings":["Institut f\u00fcr Neuroinformatik, Ruhr-Universit\u00e4t Bochum, Universit\u00e4tsstra\u00dfe 150, Bochum, Germany, --- Select a Country ---"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Institut f\u00fcr Neuroinformatik, Ruhr-Universit\u00e4t Bochum, Universit\u00e4tsstra\u00dfe 150, Bochum, Germany, --- Select a Country ---","institution_ids":["https://openalex.org/I904495901"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I904495901"],"apc_list":null,"apc_paid":null,"fwci":0.1468,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.35512642,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":93},"biblio":{"volume":null,"issue":null,"first_page":"267","last_page":"276"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994999766349792,"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":0.9994999766349792,"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":0.9896000027656555,"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/T12026","display_name":"Explainable Artificial Intelligence (XAI)","score":0.986299991607666,"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":0.7206766605377197},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6559085845947266},{"id":"https://openalex.org/keywords/representation","display_name":"Representation (politics)","score":0.620337724685669},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.5919743180274963},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.5737887024879456},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5632367134094238},{"id":"https://openalex.org/keywords/signal","display_name":"SIGNAL (programming language)","score":0.429523766040802}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7206766605377197},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6559085845947266},{"id":"https://openalex.org/C2776359362","wikidata":"https://www.wikidata.org/wiki/Q2145286","display_name":"Representation (politics)","level":3,"score":0.620337724685669},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.5919743180274963},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.5737887024879456},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5632367134094238},{"id":"https://openalex.org/C2779843651","wikidata":"https://www.wikidata.org/wiki/Q7390335","display_name":"SIGNAL (programming language)","level":2,"score":0.429523766040802},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"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/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C94625758","wikidata":"https://www.wikidata.org/wiki/Q7163","display_name":"Politics","level":2,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.5220/0010640200003063","is_oa":false,"landing_page_url":"https://doi.org/10.5220/0010640200003063","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th International Joint Conference on Computational Intelligence","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2105.03172","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.03172","pdf_url":"https://arxiv.org/pdf/2105.03172","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,"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:3163453895","is_oa":true,"landing_page_url":"http://export.arxiv.org/pdf/2105.03172","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,"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.2105.03172","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2105.03172","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,"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":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2105.03172","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2105.03172","pdf_url":"https://arxiv.org/pdf/2105.03172","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,"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":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":23,"referenced_works":["https://openalex.org/W567721252","https://openalex.org/W1191599655","https://openalex.org/W1594201624","https://openalex.org/W1757796397","https://openalex.org/W1777239053","https://openalex.org/W2002305926","https://openalex.org/W2080379318","https://openalex.org/W2081944499","https://openalex.org/W2109910161","https://openalex.org/W2113953866","https://openalex.org/W2198041288","https://openalex.org/W2257979135","https://openalex.org/W2440926996","https://openalex.org/W2736601468","https://openalex.org/W2913350117","https://openalex.org/W2960876848","https://openalex.org/W2962747693","https://openalex.org/W2963313316","https://openalex.org/W2964021598","https://openalex.org/W2984524734","https://openalex.org/W2996037775","https://openalex.org/W3092740831","https://openalex.org/W3096759198"],"related_works":["https://openalex.org/W3208494958","https://openalex.org/W3133533407","https://openalex.org/W3209125487","https://openalex.org/W2002346725","https://openalex.org/W3155957742","https://openalex.org/W2897200624","https://openalex.org/W3040033820","https://openalex.org/W2970181117","https://openalex.org/W2417936402","https://openalex.org/W2605369401","https://openalex.org/W3130271297","https://openalex.org/W3132052801","https://openalex.org/W3091628900","https://openalex.org/W2890882194","https://openalex.org/W3204272549","https://openalex.org/W2364302853","https://openalex.org/W3139073295","https://openalex.org/W3101805180","https://openalex.org/W3037755290","https://openalex.org/W2319367305"],"abstract_inverted_index":{"One":[0],"of":[1,12,22,37,77,94],"the":[2,10,43,78,92,100,120],"fundamental":[3],"challenges":[4],"in":[5,57,82,140],"reinforcement":[6],"learning":[7,53],"(RL)":[8],"is":[9,40,46,125],"one":[11],"data":[13],"efficiency:":[14],"modern":[15],"algorithms":[16],"require":[17],"a":[18,54,58,71,74,85],"very":[19],"large":[20],"number":[21],"training":[23,93],"samples,":[24],"especially":[25],"compared":[26],"to":[27,68,127],"humans,":[28],"for":[29,61,112,122],"solving":[30],"environments":[31,142],"with":[32,84,143],"high-dimensional":[33,114],"observations.":[34],"The":[35,64],"severity":[36],"this":[38,49],"problem":[39],"increased":[41],"when":[42],"reward":[44,62,65,80,101,104,123],"signal":[45,81],"sparse.":[47],"In":[48],"work,":[50],"we":[51],"propose":[52],"state":[55],"representation":[56,111],"self-supervised":[59],"manner":[60],"prediction.":[63],"predictor":[66,105,121],"learns":[67],"estimate":[69],"either":[70],"raw":[72],"or":[73],"smoothed":[75],"version":[76],"true":[79],"environment":[83],"single,":[86],"terminating,":[87],"goal":[88],"state.":[89],"We":[90],"augment":[91],"out-of-the-box":[95],"RL":[96],"agents":[97],"by":[98],"shaping":[99],"using":[102,119,132],"our":[103,110],"during":[106],"policy":[107],"learning.":[108],"Using":[109],"preprocessing":[113],"observations,":[115],"as":[116,118],"well":[117],"shaping,":[124],"shown":[126],"significantly":[128],"enhance":[129],"Actor":[130],"Critic":[131],"Kronecker-factored":[133],"Trust":[134],"Region":[135],"and":[136],"Proximal":[137],"Policy":[138],"Optimization":[139],"single-goal":[141],"visual":[144],"inputs.":[145]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}