{"id":"https://openalex.org/W7128926102","doi":"https://doi.org/10.1145/3788731.3788745","title":"TA-PPO: A Proximal Policy Optimization Method Integrating Temporal Sequence States","display_name":"TA-PPO: A Proximal Policy Optimization Method Integrating Temporal Sequence States","publication_year":2025,"publication_date":"2025-12-19","ids":{"openalex":"https://openalex.org/W7128926102","doi":"https://doi.org/10.1145/3788731.3788745"},"language":null,"primary_location":{"id":"doi:10.1145/3788731.3788745","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788731.3788745","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Embodied Intelligence and Large Models","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1145/3788731.3788745","any_repository_has_fulltext":null},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Weijun Wang","orcid":"https://orcid.org/0000-0002-7323-898X"},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Weijun Wang","raw_affiliation_strings":["College of Navigation, Jimei University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0000-0002-7323-898X","affiliations":[{"raw_affiliation_string":"College of Navigation, Jimei University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I161346416"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Mingjie Li","orcid":"https://orcid.org/0009-0002-2126-9343"},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Mingjie Li","raw_affiliation_strings":["College of Navigation, Jimei University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0009-0002-2126-9343","affiliations":[{"raw_affiliation_string":"College of Navigation, Jimei University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I161346416"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5126032087","display_name":"Bushuo Wang","orcid":null},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Bushuo Wang","raw_affiliation_strings":["College of Navigation, Jimei University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0009-0005-2269-6576","affiliations":[{"raw_affiliation_string":"College of Navigation, Jimei University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I161346416"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101303299","display_name":"Kuoyuan Zhu","orcid":null},"institutions":[{"id":"https://openalex.org/I161346416","display_name":"Jimei University","ror":"https://ror.org/03hknyb50","country_code":"CN","type":"education","lineage":["https://openalex.org/I161346416"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Kuoyuan Zhu","raw_affiliation_strings":["College of Navigation, Jimei University, Xiamen, Fujian, China"],"raw_orcid":"https://orcid.org/0009-0002-9007-7812","affiliations":[{"raw_affiliation_string":"College of Navigation, Jimei University, Xiamen, Fujian, China","institution_ids":["https://openalex.org/I161346416"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.81435132,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"86","last_page":"90"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10462","display_name":"Reinforcement Learning in Robotics","score":0.4715999960899353,"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":0.4715999960899353,"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/T12611","display_name":"Neural Networks and Reservoir Computing","score":0.06430000066757202,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.03200000151991844,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/convergence","display_name":"Convergence (economics)","score":0.7336999773979187},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.7171000242233276},{"id":"https://openalex.org/keywords/stability","display_name":"Stability (learning theory)","score":0.6399999856948853},{"id":"https://openalex.org/keywords/sequence","display_name":"Sequence (biology)","score":0.5770999789237976},{"id":"https://openalex.org/keywords/state","display_name":"State (computer science)","score":0.5195000171661377},{"id":"https://openalex.org/keywords/control","display_name":"Control (management)","score":0.5085999965667725},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4742000102996826},{"id":"https://openalex.org/keywords/simplicity","display_name":"Simplicity","score":0.4009999930858612}],"concepts":[{"id":"https://openalex.org/C2777303404","wikidata":"https://www.wikidata.org/wiki/Q759757","display_name":"Convergence (economics)","level":2,"score":0.7336999773979187},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.7171000242233276},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6805999875068665},{"id":"https://openalex.org/C112972136","wikidata":"https://www.wikidata.org/wiki/Q7595718","display_name":"Stability (learning theory)","level":2,"score":0.6399999856948853},{"id":"https://openalex.org/C2778112365","wikidata":"https://www.wikidata.org/wiki/Q3511065","display_name":"Sequence (biology)","level":2,"score":0.5770999789237976},{"id":"https://openalex.org/C48103436","wikidata":"https://www.wikidata.org/wiki/Q599031","display_name":"State (computer science)","level":2,"score":0.5195000171661377},{"id":"https://openalex.org/C2775924081","wikidata":"https://www.wikidata.org/wiki/Q55608371","display_name":"Control (management)","level":2,"score":0.5085999965667725},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4742000102996826},{"id":"https://openalex.org/C2776372474","wikidata":"https://www.wikidata.org/wiki/Q508291","display_name":"Simplicity","level":2,"score":0.4009999930858612},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.39169999957084656},{"id":"https://openalex.org/C72434380","wikidata":"https://www.wikidata.org/wiki/Q230930","display_name":"State space","level":2,"score":0.38449999690055847},{"id":"https://openalex.org/C126255220","wikidata":"https://www.wikidata.org/wiki/Q141495","display_name":"Mathematical optimization","level":1,"score":0.3549000024795532},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3452000021934509},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3303000032901764},{"id":"https://openalex.org/C137836250","wikidata":"https://www.wikidata.org/wiki/Q984063","display_name":"Optimization problem","level":2,"score":0.3203999996185303},{"id":"https://openalex.org/C196340769","wikidata":"https://www.wikidata.org/wiki/Q7698910","display_name":"Temporal difference learning","level":3,"score":0.30730000138282776},{"id":"https://openalex.org/C2779227376","wikidata":"https://www.wikidata.org/wiki/Q6505497","display_name":"Layer (electronics)","level":2,"score":0.30649998784065247},{"id":"https://openalex.org/C2778572836","wikidata":"https://www.wikidata.org/wiki/Q380933","display_name":"Space (punctuation)","level":2,"score":0.2858000099658966},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.28459998965263367},{"id":"https://openalex.org/C91575142","wikidata":"https://www.wikidata.org/wiki/Q1971426","display_name":"Optimal control","level":2,"score":0.27320000529289246},{"id":"https://openalex.org/C147764199","wikidata":"https://www.wikidata.org/wiki/Q6865248","display_name":"Minification","level":2,"score":0.2549000084400177},{"id":"https://openalex.org/C57869625","wikidata":"https://www.wikidata.org/wiki/Q1783502","display_name":"Rate of convergence","level":3,"score":0.2515999972820282}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3788731.3788745","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788731.3788745","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Embodied Intelligence and Large Models","raw_type":"proceedings-article"}],"best_oa_location":{"id":"doi:10.1145/3788731.3788745","is_oa":true,"landing_page_url":"https://doi.org/10.1145/3788731.3788745","pdf_url":null,"source":null,"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2025 International Conference on Embodied Intelligence and Large Models","raw_type":"proceedings-article"},"sustainable_development_goals":[{"score":0.7855715751647949,"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":1,"referenced_works":["https://openalex.org/W3127561923"],"related_works":[],"abstract_inverted_index":{"To":[0],"overcome":[1],"the":[2,5,37,43,55,77,82,97,112,115],"limitations":[3],"of":[4,114],"standard":[6],"Proximal":[7,31],"Policy":[8,32],"Optimization":[9],"algorithm":[10],"in":[11,19,96],"capturing":[12],"temporal":[13,58,73,117],"dependencies":[14],"and":[15,88,107],"maintaining":[16],"policy":[17,56,109],"stability":[18],"dynamic":[20],"control":[21,94],"environments,":[22],"this":[23],"paper":[24],"proposes":[25],"an":[26],"enhanced":[27],"approach":[28],"named":[29],"Temporal-Augmented":[30],"Optimization.":[33],"The":[34],"method":[35],"extends":[36],"agent\u2019s":[38],"observation":[39],"space":[40],"by":[41],"concatenating":[42],"most":[44],"recent":[45],"n":[46],"states":[47],"into":[48],"a":[49],"single":[50],"input":[51,78],"vector,":[52],"thereby":[53],"equipping":[54],"with":[57],"awareness":[59],"during":[60],"decision-making.":[61],"Unlike":[62],"conventional":[63],"PPO,":[64],"which":[65],"relies":[66],"on":[67,92],"single-step":[68],"state":[69],"inputs,":[70],"TA-PPO":[71,103],"introduces":[72],"information":[74],"solely":[75],"at":[76],"layer":[79],"without":[80],"modifying":[81],"network":[83],"architecture,":[84],"preserving":[85],"both":[86],"simplicity":[87],"adaptability.":[89],"Experimental":[90],"evaluations":[91],"multiple":[93],"tasks":[95],"OpenAI":[98],"Gym":[99],"benchmark":[100],"demonstrate":[101],"that":[102],"achieves":[104],"faster":[105],"convergence":[106],"higher":[108],"stability,":[110],"confirming":[111],"effectiveness":[113],"proposed":[116],"augmentation":[118],"mechanism.":[119]},"counts_by_year":[],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2026-02-15T00:00:00"}