{"id":"https://openalex.org/W2999882479","doi":"https://doi.org/10.1109/taai48200.2019.8959942","title":"Combining Deep Deterministic Policy Gradient with Cross-Entropy Method","display_name":"Combining Deep Deterministic Policy Gradient with Cross-Entropy Method","publication_year":2019,"publication_date":"2019-11-01","ids":{"openalex":"https://openalex.org/W2999882479","doi":"https://doi.org/10.1109/taai48200.2019.8959942","mag":"2999882479"},"language":"en","primary_location":{"id":"doi:10.1109/taai48200.2019.8959942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taai48200.2019.8959942","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Technologies and Applications of Arti\ufb01cial Intelligence (TAAI)","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/A5015485310","display_name":"Tung-Yi Lai","orcid":"https://orcid.org/0000-0003-1442-1626"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":true,"raw_author_name":"Tung-Yi Lai","raw_affiliation_strings":["Department of Computer Science, National Chiao-Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Chiao-Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5056723326","display_name":"Chu-Hsuan Hsueh","orcid":"https://orcid.org/0000-0001-8888-3116"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Chu-Hsuan Hsueh","raw_affiliation_strings":["Department of Computer Science, National Chiao-Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Chiao-Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037788653","display_name":"You-Hsuan Lin","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"You-Hsuan Lin","raw_affiliation_strings":["Department of Computer Science, National Chiao-Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Chiao-Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5034066626","display_name":"Yeong-Jia Roger Chu","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Yeong-Jia Roger Chu","raw_affiliation_strings":["Department of Computer Science, National Chiao-Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Chiao-Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047410541","display_name":"Bo-Yang Hsueh","orcid":null},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"Bo-Yang Hsueh","raw_affiliation_strings":["Department of Computer Science, National Chiao-Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Chiao-Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5016730899","display_name":"I\u2010Chen Wu","orcid":"https://orcid.org/0000-0003-2535-0587"},"institutions":[{"id":"https://openalex.org/I148366613","display_name":"National Yang Ming Chiao Tung University","ror":"https://ror.org/00se2k293","country_code":"TW","type":"education","lineage":["https://openalex.org/I148366613"]}],"countries":["TW"],"is_corresponding":false,"raw_author_name":"I-Chen Wu","raw_affiliation_strings":["Department of Computer Science, National Chiao-Tung University, Hsinchu, Taiwan"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, National Chiao-Tung University, Hsinchu, Taiwan","institution_ids":["https://openalex.org/I148366613"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5015485310"],"corresponding_institution_ids":["https://openalex.org/I148366613"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.1805231,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"518","issue":null,"first_page":"1","last_page":"5"},"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/T10653","display_name":"Robot Manipulation and Learning","score":0.9995999932289124,"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/T11689","display_name":"Adversarial Robustness in Machine Learning","score":0.992900013923645,"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":0.6941909193992615},{"id":"https://openalex.org/keywords/cross-entropy-method","display_name":"Cross-entropy method","score":0.6308023929595947},{"id":"https://openalex.org/keywords/gaussian","display_name":"Gaussian","score":0.5809446573257446},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5692122578620911},{"id":"https://openalex.org/keywords/entropy","display_name":"Entropy (arrow of time)","score":0.5677945613861084},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4660533368587494},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4646358788013458},{"id":"https://openalex.org/keywords/mathematical-optimization","display_name":"Mathematical optimization","score":0.44312265515327454},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.42438241839408875},{"id":"https://openalex.org/keywords/cross-entropy","display_name":"Cross entropy","score":0.42122209072113037},{"id":"https://openalex.org/keywords/principle-of-maximum-entropy","display_name":"Principle of maximum entropy","score":0.32623183727264404},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3185098171234131},{"id":"https://openalex.org/keywords/optimization-problem","display_name":"Optimization problem","score":0.2659473419189453},{"id":"https://openalex.org/keywords/physics","display_name":"Physics","score":0.12810972332954407},{"id":"https://openalex.org/keywords/chemistry","display_name":"Chemistry","score":0.08266198635101318},{"id":"https://openalex.org/keywords/computational-chemistry","display_name":"Computational chemistry","score":0.07677984237670898}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6941909193992615},{"id":"https://openalex.org/C75782508","wikidata":"https://www.wikidata.org/wiki/Q3333633","display_name":"Cross-entropy method","level":4,"score":0.6308023929595947},{"id":"https://openalex.org/C163716315","wikidata":"https://www.wikidata.org/wiki/Q901177","display_name":"Gaussian","level":2,"score":0.5809446573257446},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5692122578620911},{"id":"https://openalex.org/C106301342","wikidata":"https://www.wikidata.org/wiki/Q4117933","display_name":"Entropy (arrow of time)","level":2,"score":0.5677945613861084},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4660533368587494},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4646358788013458},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.44312265515327454},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.42438241839408875},{"id":"https://openalex.org/C167981619","wikidata":"https://www.wikidata.org/wiki/Q1685498","display_name":"Cross entropy","level":3,"score":0.42122209072113037},{"id":"https://openalex.org/C9679016","wikidata":"https://www.wikidata.org/wiki/Q1417473","display_name":"Principle of maximum entropy","level":2,"score":0.32623183727264404},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3185098171234131},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.2659473419189453},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.12810972332954407},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.08266198635101318},{"id":"https://openalex.org/C147597530","wikidata":"https://www.wikidata.org/wiki/Q369472","display_name":"Computational chemistry","level":1,"score":0.07677984237670898},{"id":"https://openalex.org/C98036226","wikidata":"https://www.wikidata.org/wiki/Q7268356","display_name":"Quadratic assignment problem","level":3,"score":0.0},{"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/taai48200.2019.8959942","is_oa":false,"landing_page_url":"https://doi.org/10.1109/taai48200.2019.8959942","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 International Conference on Technologies and Applications of Arti\ufb01cial Intelligence (TAAI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W1522301498","https://openalex.org/W1577352482","https://openalex.org/W2145339207","https://openalex.org/W2201581102","https://openalex.org/W2766447205","https://openalex.org/W2770616710","https://openalex.org/W2810785043","https://openalex.org/W2953384591","https://openalex.org/W2962736495","https://openalex.org/W2963864421","https://openalex.org/W6631190155","https://openalex.org/W6684921986","https://openalex.org/W6687681856","https://openalex.org/W6713134421","https://openalex.org/W6753243525"],"related_works":["https://openalex.org/W2080931671","https://openalex.org/W1584645679","https://openalex.org/W2400292122","https://openalex.org/W2770616710","https://openalex.org/W2052147111","https://openalex.org/W1980187201","https://openalex.org/W286550118","https://openalex.org/W1038253066","https://openalex.org/W2088933359","https://openalex.org/W3122506910"],"abstract_inverted_index":{"This":[0],"paper":[1,20],"proposes":[2],"a":[3,21,44,91,105],"deep":[4,28],"reinforcement":[5],"learning":[6],"algorithm":[7,65],"for":[8],"solving":[9],"robotic":[10],"tasks,":[11],"such":[12,117],"as":[13,49,69,118],"grasping":[14,110],"objects.":[15],"We":[16],"propose":[17],"in":[18,36,96],"this":[19],"combination":[22],"of":[23,78],"cross-entropy":[24],"optimization":[25],"(CE)":[26],"with":[27,47,90],"deterministic":[29],"policy":[30],"gradient":[31],"(DDPG).":[32],"More":[33],"specifically,":[34],"where":[35],"the":[37,56,70,76,87,97],"CE":[38,88,93],"method,":[39,94],"we":[40,53,81],"first":[41],"sample":[42],"from":[43],"Gaussian":[45],"distribution":[46],"zero":[48],"its":[50],"initial":[51,57],"mean,":[52],"now":[54],"set":[55],"mean":[58],"to":[59,68,74],"DDPG's":[60],"output":[61],"instead.":[62],"The":[63],"resulting":[64,95],"is":[66],"referred":[67],"DDPG-CE":[71,84],"method.":[72],"Next,":[73],"negate":[75],"effects":[77],"bad":[79],"samples,":[80],"improve":[82],"on":[83,109],"by":[85],"substituting":[86],"component":[89],"weighted":[92],"DDPG-WCE":[98,103],"algorithm.":[99],"Experiments":[100],"show":[101],"that":[102],"achieves":[104],"higher":[106],"success":[107],"rate":[108],"previously":[111],"unseen":[112],"objects,":[113],"than":[114],"other":[115],"approaches,":[116],"supervised":[119],"learning,":[120],"DDPG,":[121],"CE,":[122],"and":[123],"DDPG-CE.":[124]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}