{"id":"https://openalex.org/W2794119481","doi":null,"title":"Learning Deep Policies for Physics-Based Manipulation in Clutter.","display_name":"Learning Deep Policies for Physics-Based Manipulation in Clutter.","publication_year":2018,"publication_date":"2018-03-21","ids":{"openalex":"https://openalex.org/W2794119481","mag":"2794119481"},"language":"en","primary_location":{"id":"mag:2794119481","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1803.08100.pdf","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,"listed_in":[],"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},"volume":null,"type":"preprint","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1803.08100.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5068140202","display_name":"Wissam Bejjani","orcid":"https://orcid.org/0000-0002-6129-2460","observed_orcids":["https://orcid.org/0000-0002-6129-2460"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Wissam Bejjani","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6129-2460","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024057361","display_name":"Rafael Papallas","orcid":"https://orcid.org/0000-0003-3892-1940","observed_orcids":["https://orcid.org/0000-0003-3892-1940"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rafael Papallas","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0003-3892-1940","affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058021734","display_name":"Matteo Leonetti","orcid":"https://orcid.org/0000-0002-3831-2400","observed_orcids":["https://orcid.org/0000-0002-3831-2400"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Matteo Leonetti","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-3831-2400","affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5025603635","display_name":"Mehmet R. Do\u011far","orcid":"https://orcid.org/0000-0002-6896-5461","observed_orcids":["https://orcid.org/0000-0002-6896-5461"]},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Mehmet R. Do\u011far","raw_affiliation_strings":[],"raw_orcid":"https://orcid.org/0000-0002-6896-5461","affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"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":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":0.8935999870300293,"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":0.8935999870300293,"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":0.10419999808073044,"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/T10906","display_name":"AI-based Problem Solving and Planning","score":0.00039999998989515007,"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/cluttered-environments","display_name":"cluttered environments","score":0.5989999771118164},{"id":"https://openalex.org/keywords/imitation-learning","display_name":"imitation learning","score":0.890999972820282},{"id":"https://openalex.org/keywords/lookahead-planning","display_name":"lookahead planning","score":0.6990000009536743},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"reinforcement learning","score":0.6269999742507935},{"id":"https://openalex.org/keywords/uncertain-dynamics","display_name":"uncertain dynamics","score":0.5180000066757202},{"id":"https://openalex.org/keywords/sim-to-real-transfer","display_name":"sim-to-real transfer","score":0.6200000047683716},{"id":"https://openalex.org/keywords/robotic-manipulation","display_name":"robotic manipulation","score":0.5640000104904175}],"concepts":[{"id":"https://openalex.org/C132094186","wikidata":"https://www.wikidata.org/wiki/Q641585","display_name":"Clutter","level":3,"score":0.7468233704566956},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.6847914457321167},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6369954943656921},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6078243255615234},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5674722194671631},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5327950119972229},{"id":"https://openalex.org/C14036430","wikidata":"https://www.wikidata.org/wiki/Q3736076","display_name":"Function (biology)","level":2,"score":0.5304310321807861},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5142497420310974},{"id":"https://openalex.org/C2776999362","wikidata":"https://www.wikidata.org/wiki/Q2349274","display_name":"Planner","level":2,"score":0.513671338558197},{"id":"https://openalex.org/C126388530","wikidata":"https://www.wikidata.org/wiki/Q1131737","display_name":"Imitation","level":2,"score":0.5040639638900757},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.4332010746002197},{"id":"https://openalex.org/C14646407","wikidata":"https://www.wikidata.org/wiki/Q1430750","display_name":"Bellman equation","level":2,"score":0.42977267503738403},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4164932370185852},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.19449535012245178},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.10718020796775818},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.08977416157722473},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.08772090077400208},{"id":"https://openalex.org/C201995342","wikidata":"https://www.wikidata.org/wiki/Q682496","display_name":"Systems engineering","level":1,"score":0.07819178700447083},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","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},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C554190296","wikidata":"https://www.wikidata.org/wiki/Q47528","display_name":"Radar","level":2,"score":0.0},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"mag:2794119481","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1803.08100.pdf","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,"listed_in":[],"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}],"best_oa_location":{"id":"mag:2794119481","doi":null,"is_oa":true,"landing_page_url":"https://arxiv.org/pdf/1803.08100.pdf","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,"listed_in":[],"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},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":10,"referenced_works":["https://openalex.org/W106792269","https://openalex.org/W1522963174","https://openalex.org/W1529094214","https://openalex.org/W1597612847","https://openalex.org/W1608892862","https://openalex.org/W2216759066","https://openalex.org/W2293949132","https://openalex.org/W2551182329","https://openalex.org/W2618097077","https://openalex.org/W7124219169"],"related_works":["https://openalex.org/W3180913742","https://openalex.org/W2931838358","https://openalex.org/W2898262798","https://openalex.org/W7139911955","https://openalex.org/W2883221329","https://openalex.org/W4221161758","https://openalex.org/W2969014098","https://openalex.org/W7134899697","https://openalex.org/W2976561111","https://openalex.org/W3192201733"],"abstract_inverted_index":{"Uncertainty":[0],"in":[1,67,147,159,166],"modeling":[2],"real":[3,17,81,161],"world":[4,18,162],"physics":[5],"makes":[6],"transferring":[7],"traditional":[8],"open-loop":[9],"motion":[10],"planning":[11],"techniques":[12],"from":[13,94],"simulation":[14,150],"to":[15,49,60,73,75,115,128],"the":[16,50,71,76,80,111,130,140],"particularly":[19],"challenging.":[20],"Available":[21],"closed-loop":[22],"policy":[23,63],"learning":[24,89],"approaches,":[25],"for":[26,64],"physics-based":[27,65],"manipulation":[28,66,165],"tasks,":[29],"typically":[30],"either":[31],"focus":[32],"on":[33,39],"single":[34],"object":[35],"manipulation,":[36],"or":[37],"rely":[38],"imitation":[40,88],"learning,":[41,136],"which":[42,69,91],"inherently":[43],"constrains":[44],"task":[45,163],"generalization":[46],"and":[47],"performance":[48],"available":[51],"demonstrations.":[52],"In":[53],"this":[54],"work,":[55],"we":[56,126],"propose":[57,127],"an":[58,87,99],"approach":[59,146],"learn":[61],"a":[62,95,104,117,122,148,160],"clutter,":[68],"enables":[70],"robot":[72],"react":[74],"uncertain":[77],"dynamics":[78],"of":[79,139,164],"world.":[82],"We":[83,108,143],"start":[84],"with":[85,152],"presenting":[86],"technique":[90],"compiles":[92],"demonstrations":[93],"sampling-based":[96],"planner":[97],"into":[98],"action-value":[100,113,132],"function":[101,114,133],"encoded":[102],"as":[103,156,158],"deep":[105,131],"neural":[106],"network.":[107],"then":[109],"use":[110],"learned":[112],"guide":[116],"look-ahead":[118,141],"planner,":[119],"giving":[120],"us":[121],"control":[123],"policy.":[124],"Lastly,":[125],"refine":[129],"through":[134],"reinforcement":[135],"taking":[137],"advantage":[138],"planner.":[142],"evaluate":[144],"our":[145],"physics-enabled":[149],"environment":[151],"artificially":[153],"injected":[154],"uncertainty,":[155],"well":[157],"clutter.":[167]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-10-16T09:59:22.235173","created_date":"2018-03-29T00:00:00"}