{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T03:50:13Z","timestamp":1791345013842,"version":"4.3.1"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Robotics and Autonomous Systems"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.robot.2026.105639","type":"journal-article","created":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T15:18:09Z","timestamp":1784906289000},"page":"105639","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["An improved soft actor-retrospective critic algorithm based on the dynamic fusion priority experience replay for UAV path planning"],"prefix":"10.1016","volume":"205","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2473-1838","authenticated-orcid":false,"given":"Li","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5934-8518","authenticated-orcid":false,"given":"Chengyue","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9687-0020","authenticated-orcid":false,"given":"Guodong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5330-1056","authenticated-orcid":false,"given":"Xiaoran","family":"Kong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9047-1567","authenticated-orcid":false,"given":"Lin","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.robot.2026.105639_b1","doi-asserted-by":"crossref","DOI":"10.1016\/j.robot.2025.105076","article-title":"Fire front path planning and tracking control of Uncrewed Aerial Vehicles using deep reinforcement learning","volume":"193","author":"Raoufi","year":"2025","journal-title":"Robot. Auton. Syst."},{"issue":"12","key":"10.1016\/j.robot.2026.105639_b2","doi-asserted-by":"crossref","first-page":"769","DOI":"10.3390\/drones8120769","article-title":"Dealing with multiple optimization objectives for UAV path planning in hostile environments: A literature review","volume":"8","author":"Quadt","year":"2024","journal-title":"Drones"},{"key":"10.1016\/j.robot.2026.105639_b3","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1016\/j.actaastro.2025.07.059","article-title":"Path planning algorithm for a south pole lunar rover mission","volume":"237","author":"Chen","year":"2025","journal-title":"Acta Astronaut."},{"key":"10.1016\/j.robot.2026.105639_b4","doi-asserted-by":"crossref","first-page":"373","DOI":"10.1007\/s10514-021-10028-3","article-title":"Cooperative multi-UAV coverage mission planning platform for remote sensing applications","volume":"46","author":"Apostolidis","year":"2022","journal-title":"Auton. Robot."},{"key":"10.1016\/j.robot.2026.105639_b5","doi-asserted-by":"crossref","DOI":"10.1016\/j.swevo.2025.102051","article-title":"Reinforcement learning-integrated evolutionary algorithm for enhanced unmanned aerial vehicle coverage path planning","volume":"97","author":"Choi","year":"2025","journal-title":"Swarm Evol. Comput."},{"key":"10.1016\/j.robot.2026.105639_b6","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1109\/TCDS.2024.3442957","article-title":"UAV coverage path planning of Multiple Disconnected Regions based on cooperative optimization algorithms","volume":"17","author":"Lyu","year":"2025","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"issue":"3","key":"10.1016\/j.robot.2026.105639_b7","doi-asserted-by":"crossref","first-page":"btae032","DOI":"10.1093\/bioinformatics\/btae032","article-title":"Exact global alignment using a* with chaining seed heuristic and match pruning","volume":"40","author":"Groot Koerkamp","year":"2024","journal-title":"Bioinform."},{"issue":"6","key":"10.1016\/j.robot.2026.105639_b8","doi-asserted-by":"crossref","first-page":"9003","DOI":"10.1109\/TVT.2023.3348140","article-title":"An efficient and accurate A-star algorithm for autonomous vehicle path planning","volume":"73","author":"Lin","year":"2024","journal-title":"IEEE Trans. Veh. Technol."},{"key":"10.1016\/j.robot.2026.105639_b9","doi-asserted-by":"crossref","DOI":"10.1007\/s42235-024-00637-w","article-title":"An asynchronous genetic algorithm for multi-agent path planning inspired by biomimicry","volume":"22","author":"Liu","year":"2025","journal-title":"J. Bionic Eng."},{"key":"10.1016\/j.robot.2026.105639_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2023.110868","article-title":"A mixing algorithm of ACO and ABC for solving path planning of mobile robot","volume":"148","author":"Li","year":"2023","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.robot.2026.105639_b11","doi-asserted-by":"crossref","first-page":"2622","DOI":"10.1017\/aer.2025.10025","article-title":"A greedy initialiser based meta-heuristic approach for planning unmanned aerial vehicles","volume":"129","author":"Aslan","year":"2025","journal-title":"Aeronaut. J."},{"key":"10.1016\/j.robot.2026.105639_b12","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1007\/s10586-024-04941-2","article-title":"DUALIPA: a new immune plasma algorithm for path planning of unmanned aerial vehicles","volume":"28","author":"Aslan","year":"2025","journal-title":"Clust. Comput."},{"key":"10.1016\/j.robot.2026.105639_b13","doi-asserted-by":"crossref","first-page":"41597","DOI":"10.1038\/s41598-025-25490-7","article-title":"Swift flight optimizer: a novel bio-inspired optimization algorithm based on swift bird behavior","volume":"15","author":"Kareem","year":"2025","journal-title":"Sci. Rep."},{"key":"10.1016\/j.robot.2026.105639_b14","article-title":"A multi-population immune plasma algorithm for path planning of unmanned combat aerial vehicle","volume":"55","author":"Aslan","year":"2025","journal-title":"Adv. Eng. Inf."},{"issue":"6","key":"10.1016\/j.robot.2026.105639_b15","doi-asserted-by":"crossref","first-page":"1442","DOI":"10.1109\/TC.2024.3377895","article-title":"An integrated FPGA accelerator for deep learning-based 2D\/3D path planning","volume":"73","author":"Sugiura","year":"2024","journal-title":"IEEE Trans. Comput."},{"issue":"4","key":"10.1016\/j.robot.2026.105639_b16","first-page":"4396","article-title":"Domain generalization: A survey","volume":"45","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"7976","key":"10.1016\/j.robot.2026.105639_b17","doi-asserted-by":"crossref","first-page":"982","DOI":"10.1038\/s41586-023-06419-4","article-title":"Champion-level drone racing using deep reinforcement learning","volume":"620","author":"Kaufmann","year":"2023","journal-title":"Nature"},{"key":"10.1016\/j.robot.2026.105639_b18","doi-asserted-by":"crossref","first-page":"690","DOI":"10.1016\/j.actaastro.2025.09.046","article-title":"Fuel-aware autonomous docking using RL-augmented MPC rewards for on-orbit refueling","volume":"238","author":"Ramezani","year":"2026","journal-title":"Acta Astronaut."},{"issue":"11","key":"10.1016\/j.robot.2026.105639_b19","doi-asserted-by":"crossref","first-page":"2649","DOI":"10.1111\/2041-210X.13954","article-title":"Deep reinforcement learning for conservation decisions","volume":"13","author":"Lapeyrolerie","year":"2022","journal-title":"Methods Ecol. Evol."},{"issue":"7","key":"10.1016\/j.robot.2026.105639_b20","doi-asserted-by":"crossref","first-page":"8762","DOI":"10.1109\/TNNLS.2023.3236361","article-title":"Exploration in deep reinforcement learning: From single-agent to multiagent domain","volume":"35","author":"Hao","year":"2024","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.robot.2026.105639_b21","doi-asserted-by":"crossref","first-page":"327","DOI":"10.1017\/S0962492921000052","article-title":"Neural network approximation","volume":"30","author":"DeVore","year":"2021","journal-title":"Acta Numer."},{"key":"10.1016\/j.robot.2026.105639_b22","series-title":"Randomized ensembled double Q-learning: Learning fast without a model","author":"Chen","year":"2021"},{"key":"10.1016\/j.robot.2026.105639_b23","series-title":"Stochastic Q-learning for large discrete action spaces","author":"Fourati","year":"2024"},{"key":"10.1016\/j.robot.2026.105639_b24","doi-asserted-by":"crossref","DOI":"10.1016\/j.ast.2025.111295","article-title":"Taxiway path planning at airports based on dynamic directed graphs and DQN","volume":"168","author":"Shen","year":"2026","journal-title":"Aerosp. Sci. Technol."},{"issue":"24","key":"10.1016\/j.robot.2026.105639_b25","doi-asserted-by":"crossref","first-page":"53262","DOI":"10.1109\/JIOT.2025.3616362","article-title":"Multiobjective optimization of path planning and communication capacity based on DQN with weighted prioritized experience replay","volume":"12","author":"Lu","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.robot.2026.105639_b26","first-page":"1","article-title":"AGV path planning with dynamic obstacles based on deep Q-network and distributed training","volume":"12","author":"Xie","year":"2025","journal-title":"Int. J. Pr. Eng. Man-Gt."},{"key":"10.1016\/j.robot.2026.105639_b27","doi-asserted-by":"crossref","first-page":"12606","DOI":"10.1109\/TASE.2025.3547250","article-title":"Online monitoring of high-dimensional data streams with deep Q-network","volume":"22","author":"Li","year":"2025","journal-title":"IEEE Trans. Autom. Sci. Eng."},{"issue":"4","key":"10.1016\/j.robot.2026.105639_b28","doi-asserted-by":"crossref","first-page":"1421","DOI":"10.3390\/app14041421","article-title":"Deep Q-learning-based smart scheduling of EVs for demand response in smart grids","volume":"14","author":"Chifu","year":"2024","journal-title":"Appl. Sci."},{"key":"10.1016\/j.robot.2026.105639_b29","series-title":"Sample efficient reinforcement learning with REINFORCE","author":"Zhang","year":"2020"},{"key":"10.1016\/j.robot.2026.105639_b30","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1016\/j.actaastro.2024.08.015","article-title":"Path planning of 6-DOF free-floating space robotic manipulators using reinforcement learning","volume":"224","author":"Al Ali","year":"2024","journal-title":"Acta Astronaut."},{"key":"10.1016\/j.robot.2026.105639_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2023.110601","article-title":"Immune deep reinforcement learning-based path planning for mobile robot in unknown environment","volume":"145","author":"Yan","year":"2023","journal-title":"Appl. Soft Comput."},{"issue":"9","key":"10.1016\/j.robot.2026.105639_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.cja.2025.103484","article-title":"Large-scale UAV swarm path planning based on mean-field reinforcement learning","volume":"38","author":"Zhang","year":"2025","journal-title":"Chin. J. Aeronaut."},{"key":"10.1016\/j.robot.2026.105639_b33","article-title":"Emergency fire escape path planning model based on improved ddpg algorithm","volume":"95","author":"Feng","year":"2024","journal-title":"J. Build. Eng."},{"key":"10.1016\/j.robot.2026.105639_b34","first-page":"1","article-title":"TD3 agent-based nonlinear dynamic inverse control for fixed-wing uav attitudes","author":"Hu","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"4","key":"10.1016\/j.robot.2026.105639_b35","doi-asserted-by":"crossref","first-page":"1397","DOI":"10.1109\/JOE.2024.3436770","article-title":"Proximal policy-optimized regularized least squares algorithm for noise-resilient motion prediction of UMVs","volume":"49","author":"Zhong","year":"2024","journal-title":"IEEE J. Ocean. Eng."},{"key":"10.1016\/j.robot.2026.105639_b36","doi-asserted-by":"crossref","DOI":"10.1016\/j.oceaneng.2025.120907","article-title":"Dynamic path planning for multi-USV in complex ocean environments with limited perception via proximal policy optimization","volume":"326","author":"Chen","year":"2025","journal-title":"Ocean Eng."},{"issue":"7","key":"10.1016\/j.robot.2026.105639_b37","first-page":"1720","article-title":"A multi-AGV routing planning method based on deep reinforcement learning and recurrent neural network","volume":"11","author":"Lin","year":"2024","journal-title":"IEEE-CAA J. Autom."},{"key":"10.1016\/j.robot.2026.105639_b38","doi-asserted-by":"crossref","DOI":"10.1016\/j.measurement.2025.119765","article-title":"Intelligent path planning based on joint threat avoidance and multi-target tracking optimization","volume":"260","author":"Chen","year":"2026","journal-title":"Measurement"},{"key":"10.1016\/j.robot.2026.105639_b39","doi-asserted-by":"crossref","DOI":"10.1016\/j.ast.2025.110327","article-title":"Dynamic and adaptive learning for autonomous decision-making in beyond visual range air combat","volume":"163","author":"Wang","year":"2025","journal-title":"Aerosp. Sci. Technol."},{"key":"10.1016\/j.robot.2026.105639_b40","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/j.neucom.2023.03.054","article-title":"Action decoupled SAC reinforcement learning with discrete-continuous hybrid action spaces","volume":"537","author":"Xu","year":"2023","journal-title":"Neurocomputing"},{"issue":"10","key":"10.1016\/j.robot.2026.105639_b41","doi-asserted-by":"crossref","first-page":"15568","DOI":"10.1109\/TITS.2025.3587447","article-title":"Curiosity-driven distributional soft actor-critic for AUV anti-disturbance path tracking","volume":"26","author":"Hou","year":"2025","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.robot.2026.105639_b42","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1007\/s10434-999-0127-z","article-title":"Retrospective reviews can be learning experiences","volume":"6","author":"Petrelli","year":"1999","journal-title":"Ann. Surg. Oncol."},{"key":"10.1016\/j.robot.2026.105639_b43","series-title":"Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor","author":"Haarnoja","year":"2018"}],"container-title":["Robotics and Autonomous Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0921889026003118?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0921889026003118?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T02:58:48Z","timestamp":1791341928000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0921889026003118"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":43,"alternative-id":["S0921889026003118"],"URL":"https:\/\/doi.org\/10.1016\/j.robot.2026.105639","relation":{},"ISSN":["0921-8890"],"issn-type":[{"value":"0921-8890","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"An improved soft actor-retrospective critic algorithm based on the dynamic fusion priority experience replay for UAV path planning","name":"articletitle","label":"Article Title"},{"value":"Robotics and Autonomous Systems","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.robot.2026.105639","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"105639"}}