{"id":"https://openalex.org/W2901563868","doi":"https://doi.org/10.1109/ictc.2018.8539438","title":"Combining Reward Shaping and Curriculum Learning for Training Agents with High Dimensional Continuous Action Spaces","display_name":"Combining Reward Shaping and Curriculum Learning for Training Agents with High Dimensional Continuous Action Spaces","publication_year":2018,"publication_date":"2018-10-01","ids":{"openalex":"https://openalex.org/W2901563868","doi":"https://doi.org/10.1109/ictc.2018.8539438","mag":"2901563868"},"language":"en","primary_location":{"id":"doi:10.1109/ictc.2018.8539438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc.2018.8539438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"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/A5070677616","display_name":"Sooyoung Jang","orcid":"https://orcid.org/0000-0002-6931-9592"},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Sooyoung Jang","raw_affiliation_strings":["IoT Research Division, Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"IoT Research Division, Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I142401562"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5112677842","display_name":"Mikyong Han","orcid":null},"institutions":[{"id":"https://openalex.org/I142401562","display_name":"Electronics and Telecommunications Research Institute","ror":"https://ror.org/03ysstz10","country_code":"KR","type":"facility","lineage":["https://openalex.org/I142401562","https://openalex.org/I2801339556","https://openalex.org/I4210144908","https://openalex.org/I4387152098"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Mikyong Han","raw_affiliation_strings":["IoT Research Division, Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea"],"affiliations":[{"raw_affiliation_string":"IoT Research Division, Electronics and Telecommunications Research Institute (ETRI), Daejeon, Republic of Korea","institution_ids":["https://openalex.org/I142401562"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5070677616"],"corresponding_institution_ids":["https://openalex.org/I142401562"],"apc_list":null,"apc_paid":null,"fwci":0.6515,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.77461721,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1391","last_page":"1393"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9994000196456909,"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":0.9994000196456909,"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9965999722480774,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.9855999946594238,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/task","display_name":"Task (project management)","score":0.7103077173233032},{"id":"https://openalex.org/keywords/curriculum","display_name":"Curriculum","score":0.6793299913406372},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6752938032150269},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.6664556264877319},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.5789039134979248},{"id":"https://openalex.org/keywords/scheme","display_name":"Scheme (mathematics)","score":0.567969799041748},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5643242597579956},{"id":"https://openalex.org/keywords/function","display_name":"Function (biology)","score":0.5301186442375183},{"id":"https://openalex.org/keywords/training","display_name":"Training (meteorology)","score":0.4773443043231964},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.45049041509628296},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.44834089279174805},{"id":"https://openalex.org/keywords/human\u2013computer-interaction","display_name":"Human\u2013computer interaction","score":0.44639503955841064},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.14964395761489868},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.09215563535690308},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.0767987072467804}],"concepts":[{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.7103077173233032},{"id":"https://openalex.org/C47177190","wikidata":"https://www.wikidata.org/wiki/Q207137","display_name":"Curriculum","level":2,"score":0.6793299913406372},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6752938032150269},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.6664556264877319},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.5789039134979248},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.567969799041748},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5643242597579956},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5301186442375183},{"id":"https://openalex.org/C2777211547","wikidata":"https://www.wikidata.org/wiki/Q17141490","display_name":"Training (meteorology)","level":2,"score":0.4773443043231964},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.45049041509628296},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.44834089279174805},{"id":"https://openalex.org/C107457646","wikidata":"https://www.wikidata.org/wiki/Q207434","display_name":"Human\u2013computer interaction","level":1,"score":0.44639503955841064},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.14964395761489868},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.09215563535690308},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0767987072467804},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C153294291","wikidata":"https://www.wikidata.org/wiki/Q25261","display_name":"Meteorology","level":1,"score":0.0},{"id":"https://openalex.org/C19417346","wikidata":"https://www.wikidata.org/wiki/Q7922","display_name":"Pedagogy","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","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/C78458016","wikidata":"https://www.wikidata.org/wiki/Q840400","display_name":"Evolutionary biology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/ictc.2018.8539438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/ictc.2018.8539438","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 International Conference on Information and Communication Technology Convergence (ICTC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4699999988079071,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W1777239053","https://openalex.org/W2257979135","https://openalex.org/W2296073425","https://openalex.org/W2615547864","https://openalex.org/W2736601468","https://openalex.org/W2889987506","https://openalex.org/W6638088447","https://openalex.org/W6741002519","https://openalex.org/W6753526802"],"related_works":["https://openalex.org/W4293149836","https://openalex.org/W2543479404","https://openalex.org/W2031129854","https://openalex.org/W2416943787","https://openalex.org/W1804325819","https://openalex.org/W2166791242","https://openalex.org/W2323122434","https://openalex.org/W2626492911","https://openalex.org/W2102384057","https://openalex.org/W2766330485"],"abstract_inverted_index":{"The":[0,89],"needs":[1],"for":[2,57],"training":[3],"agent":[4,56,73,85],"with":[5],"high":[6],"dimensional":[7],"continuous":[8],"action":[9],"spaces":[10],"will":[11],"increase":[12],"as":[13,18],"the":[14,39,50,55,63,66,72,84,94,98],"robot":[15],"hardware":[16],"such":[17],"robotic":[19],"arms":[20],"and":[21,27,34,45,62,78],"humanoid":[22],"robots":[23],"are":[24,52,80],"becoming":[25],"more":[26,28],"sophisticated.":[29],"However,":[30],"it":[31,60],"is":[32],"difficult":[33],"time-consuming":[35],"task.":[36],"To":[37],"tackle":[38],"problem,":[40],"we":[41],"combine":[42],"reward":[43,76],"shaping":[44],"curriculum":[46,79],"learning.":[47,74],"More":[48],"specifically,":[49],"rewards":[51],"provided":[53],"to":[54,82],"every":[58],"step":[59],"takes":[61],"difficulty":[64],"of":[65],"problem":[67],"gradually":[68],"increases":[69],"depending":[70],"on":[71],"Both":[75],"function":[77],"designed":[81],"make":[83],"achieve":[86],"its":[87],"objective.":[88],"simulation":[90],"results":[91],"demonstrate":[92],"that":[93],"proposed":[95],"scheme":[96],"outperforms":[97],"comparisons.":[99]},"counts_by_year":[{"year":2024,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}