{"id":"https://openalex.org/W2975593154","doi":"https://doi.org/10.1109/cig.2019.8848127","title":"A Reinforcement Learning Approach To Synthesizing Climbing Movements","display_name":"A Reinforcement Learning Approach To Synthesizing Climbing Movements","publication_year":2019,"publication_date":"2019-08-01","ids":{"openalex":"https://openalex.org/W2975593154","doi":"https://doi.org/10.1109/cig.2019.8848127","mag":"2975593154"},"language":"en","primary_location":{"id":"doi:10.1109/cig.2019.8848127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cig.2019.8848127","pdf_url":null,"source":{"id":"https://openalex.org/S4306498491","display_name":"2019 IEEE Conference on Games (CoG)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://research.aalto.fi/files/38172752/SCI_Naderi_A_Reinforcement.2019.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5069822000","display_name":"Kourosh Naderi","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":true,"raw_author_name":"Kourosh Naderi","raw_affiliation_strings":["Department of Computer Science, Aalto University, Helsinki, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Helsinki, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058061575","display_name":"Amin Babadi","orcid":"https://orcid.org/0000-0003-4930-9917"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Amin Babadi","raw_affiliation_strings":["Department of Computer Science, Aalto University, Helsinki, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Helsinki, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5024645419","display_name":"Shaghayegh Roohi","orcid":null},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Shaghayegh Roohi","raw_affiliation_strings":["Department of Computer Science, Aalto University, Helsinki, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Helsinki, Finland","institution_ids":["https://openalex.org/I9927081"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5060951467","display_name":"Perttu H\u00e4m\u00e4l\u00e4inen","orcid":"https://orcid.org/0000-0001-7764-3459"},"institutions":[{"id":"https://openalex.org/I9927081","display_name":"Aalto University","ror":"https://ror.org/020hwjq30","country_code":"FI","type":"education","lineage":["https://openalex.org/I9927081"]}],"countries":["FI"],"is_corresponding":false,"raw_author_name":"Perttu Hamalainen","raw_affiliation_strings":["Department of Computer Science, Aalto University, Helsinki, Finland"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Aalto University, Helsinki, Finland","institution_ids":["https://openalex.org/I9927081"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5069822000"],"corresponding_institution_ids":["https://openalex.org/I9927081"],"apc_list":null,"apc_paid":null,"fwci":0.3998,"has_fulltext":true,"cited_by_count":7,"citation_normalized_percentile":{"value":0.68742616,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"7"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.9961000084877014,"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":0.9961000084877014,"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/T12290","display_name":"Human Motion and Animation","score":0.9955000281333923,"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/T10812","display_name":"Human Pose and Action Recognition","score":0.993399977684021,"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/climbing","display_name":"Climbing","score":0.855621337890625},{"id":"https://openalex.org/keywords/reinforcement-learning","display_name":"Reinforcement learning","score":0.8001995086669922},{"id":"https://openalex.org/keywords/initialization","display_name":"Initialization","score":0.7748924493789673},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7446305751800537},{"id":"https://openalex.org/keywords/hill-climbing","display_name":"Hill climbing","score":0.7098444104194641},{"id":"https://openalex.org/keywords/humanoid-robot","display_name":"Humanoid robot","score":0.6678746938705444},{"id":"https://openalex.org/keywords/reset","display_name":"Reset (finance)","score":0.6613447070121765},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6294320821762085},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.47558414936065674},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.44647398591041565},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3891925811767578},{"id":"https://openalex.org/keywords/robot","display_name":"Robot","score":0.28127989172935486},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.11713805794715881}],"concepts":[{"id":"https://openalex.org/C95038775","wikidata":"https://www.wikidata.org/wiki/Q22857","display_name":"Climbing","level":2,"score":0.855621337890625},{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.8001995086669922},{"id":"https://openalex.org/C114466953","wikidata":"https://www.wikidata.org/wiki/Q6034165","display_name":"Initialization","level":2,"score":0.7748924493789673},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7446305751800537},{"id":"https://openalex.org/C135450995","wikidata":"https://www.wikidata.org/wiki/Q820272","display_name":"Hill climbing","level":2,"score":0.7098444104194641},{"id":"https://openalex.org/C60692881","wikidata":"https://www.wikidata.org/wiki/Q584529","display_name":"Humanoid robot","level":3,"score":0.6678746938705444},{"id":"https://openalex.org/C2779795794","wikidata":"https://www.wikidata.org/wiki/Q7315343","display_name":"Reset (finance)","level":2,"score":0.6613447070121765},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6294320821762085},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.47558414936065674},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.44647398591041565},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3891925811767578},{"id":"https://openalex.org/C90509273","wikidata":"https://www.wikidata.org/wiki/Q11012","display_name":"Robot","level":2,"score":0.28127989172935486},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.11713805794715881},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","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/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C106159729","wikidata":"https://www.wikidata.org/wiki/Q2294553","display_name":"Financial economics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cig.2019.8848127","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cig.2019.8848127","pdf_url":null,"source":{"id":"https://openalex.org/S4306498491","display_name":"2019 IEEE Conference on Games (CoG)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE Conference on Games (CoG)","raw_type":"proceedings-article"},{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/41196","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/fa2fbe51-f179-4efd-9c4f-fe325b19ffc7","pdf_url":"https://research.aalto.fi/files/38172752/SCI_Naderi_A_Reinforcement.2019.pdf","source":{"id":"https://openalex.org/S4306401663","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"}],"best_oa_location":{"id":"pmh:oai:aaltodoc.aalto.fi:123456789/41196","is_oa":true,"landing_page_url":"https://research.aalto.fi/en/publications/fa2fbe51-f179-4efd-9c4f-fe325b19ffc7","pdf_url":"https://research.aalto.fi/files/38172752/SCI_Naderi_A_Reinforcement.2019.pdf","source":{"id":"https://openalex.org/S4306401663","display_name":"Aaltodoc (Aalto University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I9927081","host_organization_name":"Aalto University","host_organization_lineage":["https://openalex.org/I9927081"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"acceptedVersion"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W2975593154.pdf","grobid_xml":"https://content.openalex.org/works/W2975593154.grobid-xml"},"referenced_works_count":38,"referenced_works":["https://openalex.org/W1771410628","https://openalex.org/W2014191197","https://openalex.org/W2042408133","https://openalex.org/W2123178778","https://openalex.org/W2138419444","https://openalex.org/W2145339207","https://openalex.org/W2173248099","https://openalex.org/W2257979135","https://openalex.org/W2726809079","https://openalex.org/W2736601468","https://openalex.org/W2739232183","https://openalex.org/W2766447205","https://openalex.org/W2767178383","https://openalex.org/W2781585732","https://openalex.org/W2781726626","https://openalex.org/W2785738552","https://openalex.org/W2796290181","https://openalex.org/W2889987506","https://openalex.org/W2890085317","https://openalex.org/W2895279298","https://openalex.org/W2902286283","https://openalex.org/W2904246096","https://openalex.org/W2947767784","https://openalex.org/W2963864421","https://openalex.org/W3104515094","https://openalex.org/W4250901985","https://openalex.org/W4289422968","https://openalex.org/W6638018090","https://openalex.org/W6684921986","https://openalex.org/W6741002519","https://openalex.org/W6747387971","https://openalex.org/W6747473740","https://openalex.org/W6747924173","https://openalex.org/W6753526802","https://openalex.org/W6756397360","https://openalex.org/W6757592117","https://openalex.org/W6763366428","https://openalex.org/W6780559895"],"related_works":["https://openalex.org/W350273603","https://openalex.org/W2393495588","https://openalex.org/W643038845","https://openalex.org/W3204184292","https://openalex.org/W96259911","https://openalex.org/W2143761673","https://openalex.org/W2521924929","https://openalex.org/W4317738234","https://openalex.org/W3156781616","https://openalex.org/W2020542318"],"abstract_inverted_index":{"This":[0],"paper":[1],"addresses":[2],"the":[3,12,17,25,47,77,112],"problem":[4],"of":[5,19,53,114],"synthesizing":[6],"simulated":[7,36],"humanoid":[8,37],"climbing":[9,21,38],"movements":[10,102],"given":[11],"target":[13],"holds,":[14],"e.g.,":[15],"by":[16],"player":[18],"a":[20,73,94],"game.":[22],"We":[23],"contribute":[24],"first":[26],"deep":[27],"reinforcement":[28],"learning":[29,105],"solution":[30],"that":[31,91],"can":[32,98],"handle":[33],"interactive":[34],"physically":[35],"with":[39,93],"more":[40],"than":[41],"one":[42],"limb":[43],"switching":[44],"holds":[45],"at":[46,111],"same":[48],"time.":[49],"A":[50],"key":[51],"component":[52],"our":[54],"approach":[55,75],"is":[56,79],"Self-Supervised":[57],"Episode":[58],"State":[59],"Initialization":[60],"(SS-":[61],"ESI),":[62],"which":[63],"ensures":[64],"diverse":[65],"exploration":[66],"and":[67,103],"speeds":[68],"up":[69],"learning,":[70],"compared":[71],"to":[72,81],"baseline":[74],"where":[76],"climber":[78],"reset":[80],"an":[82],"initial":[83],"pose":[84],"after":[85],"failure.":[86],"Our":[87],"results":[88],"also":[89],"show":[90],"training":[92],"multi-step":[95],"action":[96],"parameterization":[97],"produce":[99],"both":[100],"smoother":[101],"enable":[104],"from":[106],"slightly":[107],"fewer":[108],"explored":[109],"actions":[110],"cost":[113],"increased":[115],"simulation":[116],"time":[117],"per":[118],"action.":[119]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-03-29T08:15:47.926485","created_date":"2025-10-10T00:00:00"}