{"id":"https://openalex.org/W7125897899","doi":"https://doi.org/10.1109/smc58881.2025.11343216","title":"AGS-MADDPG: Multi-Agent Path Finding with Partially Observations Based on Attention Mechanism and Reinforcement Learning","display_name":"AGS-MADDPG: Multi-Agent Path Finding with Partially Observations Based on Attention Mechanism and Reinforcement Learning","publication_year":2025,"publication_date":"2025-10-05","ids":{"openalex":"https://openalex.org/W7125897899","doi":"https://doi.org/10.1109/smc58881.2025.11343216"},"language":null,"primary_location":{"id":"doi:10.1109/smc58881.2025.11343216","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5124107661","display_name":"Jianguo Gong","orcid":null},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianguo Gong","raw_affiliation_strings":["Chang’an University,School of Information Engineering,Xi’an,China,710064"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang’an University,School of Information Engineering,Xi’an,China,710064","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5099450346","display_name":"Yisheng An","orcid":null},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yisheng An","raw_affiliation_strings":["Chang’an University,School of Information Engineering,Xi’an,China,710064"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang’an University,School of Information Engineering,Xi’an,China,710064","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100439832","display_name":"Pei Li","orcid":"https://orcid.org/0000-0001-8699-8825"},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Peng Li","raw_affiliation_strings":["Chang’an University,School of Information Engineering,Xi’an,China,710064"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang’an University,School of Information Engineering,Xi’an,China,710064","institution_ids":["https://openalex.org/I25355098"]}]},{"author_position":"last","author":{"id":null,"display_name":"Tao Zhang","orcid":null},"institutions":[{"id":"https://openalex.org/I25355098","display_name":"Chang'an University","ror":"https://ror.org/05mxya461","country_code":"CN","type":"education","lineage":["https://openalex.org/I25355098"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Tao Zhang","raw_affiliation_strings":["Chang’an University,School of Information Engineering,Xi’an,China,710064"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Chang’an University,School of Information Engineering,Xi’an,China,710064","institution_ids":["https://openalex.org/I25355098"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I25355098"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"252","last_page":"257"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.5410000085830688,"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"}},"topics":[{"id":"https://openalex.org/T10586","display_name":"Robotic Path Planning Algorithms","score":0.5410000085830688,"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"}},{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.13819999992847443,"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/T11714","display_name":"Multimodal Machine Learning Applications","score":0.05000000074505806,"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/reinforcement-learning","display_name":"Reinforcement learning","score":0.7706999778747559},{"id":"https://openalex.org/keywords/differentiable-function","display_name":"Differentiable function","score":0.6603999733924866},{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.6238999962806702},{"id":"https://openalex.org/keywords/weighting","display_name":"Weighting","score":0.5974000096321106},{"id":"https://openalex.org/keywords/face","display_name":"Face (sociological concept)","score":0.5746999979019165},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.5697000026702881},{"id":"https://openalex.org/keywords/action","display_name":"Action (physics)","score":0.5318999886512756},{"id":"https://openalex.org/keywords/baseline","display_name":"Baseline (sea)","score":0.49140000343322754},{"id":"https://openalex.org/keywords/trajectory","display_name":"Trajectory","score":0.4733999967575073}],"concepts":[{"id":"https://openalex.org/C97541855","wikidata":"https://www.wikidata.org/wiki/Q830687","display_name":"Reinforcement learning","level":2,"score":0.7706999778747559},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6991000175476074},{"id":"https://openalex.org/C202615002","wikidata":"https://www.wikidata.org/wiki/Q783507","display_name":"Differentiable function","level":2,"score":0.6603999733924866},{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.6238999962806702},{"id":"https://openalex.org/C183115368","wikidata":"https://www.wikidata.org/wiki/Q856577","display_name":"Weighting","level":2,"score":0.5974000096321106},{"id":"https://openalex.org/C2779304628","wikidata":"https://www.wikidata.org/wiki/Q3503480","display_name":"Face (sociological concept)","level":2,"score":0.5746999979019165},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.5697000026702881},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5497999787330627},{"id":"https://openalex.org/C2780791683","wikidata":"https://www.wikidata.org/wiki/Q846785","display_name":"Action (physics)","level":2,"score":0.5318999886512756},{"id":"https://openalex.org/C12725497","wikidata":"https://www.wikidata.org/wiki/Q810247","display_name":"Baseline (sea)","level":2,"score":0.49140000343322754},{"id":"https://openalex.org/C13662910","wikidata":"https://www.wikidata.org/wiki/Q193139","display_name":"Trajectory","level":2,"score":0.4733999967575073},{"id":"https://openalex.org/C166109690","wikidata":"https://www.wikidata.org/wiki/Q4677422","display_name":"Action selection","level":3,"score":0.450300008058548},{"id":"https://openalex.org/C25321074","wikidata":"https://www.wikidata.org/wiki/Q1969601","display_name":"Pathfinding","level":4,"score":0.4207000136375427},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.41659998893737793},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.35510000586509705},{"id":"https://openalex.org/C89611455","wikidata":"https://www.wikidata.org/wiki/Q6804646","display_name":"Mechanism (biology)","level":2,"score":0.3246999979019165},{"id":"https://openalex.org/C81074085","wikidata":"https://www.wikidata.org/wiki/Q366872","display_name":"Motion planning","level":3,"score":0.31459999084472656},{"id":"https://openalex.org/C70136482","wikidata":"https://www.wikidata.org/wiki/Q13583781","display_name":"A-weighting","level":3,"score":0.3041999936103821},{"id":"https://openalex.org/C52970973","wikidata":"https://www.wikidata.org/wiki/Q2497134","display_name":"Adaptive system","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.29589998722076416},{"id":"https://openalex.org/C22367795","wikidata":"https://www.wikidata.org/wiki/Q7625208","display_name":"Structured prediction","level":2,"score":0.2770000100135803},{"id":"https://openalex.org/C32848918","wikidata":"https://www.wikidata.org/wiki/Q845789","display_name":"Observable","level":2,"score":0.2741999924182892},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.27309998869895935},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.26899999380111694},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.26100000739097595},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.25839999318122864},{"id":"https://openalex.org/C67203356","wikidata":"https://www.wikidata.org/wiki/Q1321905","display_name":"Reinforcement","level":2,"score":0.25099998712539673}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/smc58881.2025.11343216","is_oa":false,"landing_page_url":"https://doi.org/10.1109/smc58881.2025.11343216","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 IEEE International Conference on Systems, Man, and Cybernetics (SMC)","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":21,"referenced_works":["https://openalex.org/W1488757178","https://openalex.org/W1551562380","https://openalex.org/W1973396716","https://openalex.org/W1989407213","https://openalex.org/W2155336942","https://openalex.org/W2403254675","https://openalex.org/W2808589448","https://openalex.org/W2892258706","https://openalex.org/W2964997335","https://openalex.org/W3092786062","https://openalex.org/W3100789280","https://openalex.org/W3110643301","https://openalex.org/W3111843786","https://openalex.org/W3129616587","https://openalex.org/W3176143362","https://openalex.org/W4221155367","https://openalex.org/W4285613176","https://openalex.org/W4321483908","https://openalex.org/W4321608219","https://openalex.org/W4386322136","https://openalex.org/W4408047714"],"related_works":[],"abstract_inverted_index":{"We":[0,36],"proposes":[1],"Attention":[2],"Gumbel-Softmax":[3,45],"Multi-Agent":[4],"Deep":[5],"Deterministic":[6],"Policy":[7],"Gradient":[8],"(AGS-MADDPG),":[9],"a":[10],"multi-agent":[11,121],"reinforcement":[12],"learning":[13],"algorithm":[14],"for":[15,46,120],"collaborative":[16],"pathfinding":[17,95],"under":[18],"partial":[19],"observability.":[20],"Traditional":[21],"methods":[22],"face":[23],"challenges":[24],"including":[25],"non-differentiable":[26],"policy":[27,48],"gradients":[28],"and":[29,50,78,88,98],"inefficient":[30],"exploration":[31,52],"in":[32,60,82,123],"discrete":[33,114],"action":[34,72],"spaces.":[35],"address":[37],"these":[38],"by":[39,68],"integrating":[40],"the":[41,61,109],"MADDPG":[42],"framework":[43],"with":[44,85,116],"differentiable":[47,113],"optimization":[49],"adaptive":[51],"via":[53],"temperature":[54],"annealing.":[55],"A":[56],"multi-head":[57],"attention":[58],"mechanism":[59],"critic":[62],"network":[63],"explicitly":[64],"models":[65],"inter-agent":[66],"dependencies":[67],"dynamically":[69],"weighting":[70],"teammates\u2019":[71],"features,":[73],"enhancing":[74],"Q-value":[75],"estimation":[76],"precision":[77],"training":[79],"stability.":[80],"Evaluations":[81],"Pogema":[83],"environments":[84],"random":[86],"obstacles":[87],"complex":[89],"layouts":[90],"demonstrate":[91],"improved":[92],"convergence":[93],"speed,":[94],"success":[96],"rates,":[97],"average":[99],"path":[100],"length":[101],"compared":[102],"to":[103],"baseline":[104],"methods.":[105],"The":[106],"results":[107],"validate":[108],"effectiveness":[110],"of":[111],"combining":[112],"policies":[115],"explicit":[117],"attention-based":[118],"coordination":[119],"collaboration":[122],"partially":[124],"observable":[125],"settings.":[126]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2026-01-29T00:00:00"}