{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T01:03:01Z","timestamp":1782522181000,"version":"3.54.5"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/100010002","name":"Ministry of Education","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100010002","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006397","name":"National Taiwan Normal University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100006397","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["MOST 108\\u20132634-F-003-002"],"award-info":[{"award-number":["MOST 108\\u20132634-F-003-002"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["107\\u20132811-E-003-503"],"award-info":[{"award-number":["107\\u20132811-E-003-503"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["108\\u20132634-F-003-004"],"award-info":[{"award-number":["108\\u20132634-F-003-004"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["108\\u20132634-F-003-003"],"award-info":[{"award-number":["108\\u20132634-F-003-003"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004663","name":"Ministry of Science and Technology, Taiwan","doi-asserted-by":"publisher","award":["MOST 113\\u20132221-E-003-009"],"award-info":[{"award-number":["MOST 113\\u20132221-E-003-009"]}],"id":[{"id":"10.13039\/501100004663","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100020595","name":"Taiwan Ministry of Science and Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100020595","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Soft Computing"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1016\/j.asoc.2026.115093","type":"journal-article","created":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T08:24:25Z","timestamp":1774599865000},"page":"115093","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["A dual-actor proximal policy optimization algorithm for humanoid robot navigation control"],"prefix":"10.1016","volume":"196","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3360-1892","authenticated-orcid":false,"given":"Jacky","family":"Baltes","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-3379-4950","authenticated-orcid":false,"given":"Ilham","family":"Akbar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8294-8625","authenticated-orcid":false,"given":"Saeed","family":"Saeedvand","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.asoc.2026.115093_bib0005","doi-asserted-by":"crossref","first-page":"e20","DOI":"10.1017\/S0269888919000158","article-title":"A comprehensive survey on humanoid robot development","volume":"34","author":"Saeedvand","year":"2019","journal-title":"Knowl. Eng. Rev."},{"key":"10.1016\/j.asoc.2026.115093_bib0010","series-title":"Deepwalk: Omnidirectional Bipedal Gait by Deep Reinforcement Learning","author":"Rodriguez","year":"2021"},{"key":"10.1016\/j.asoc.2026.115093_bib0015","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.106941","article-title":"A deep reinforcement learning algorithm to control a two-wheeled scooter with a humanoid robot","volume":"126","author":"Baltes","year":"2023","journal-title":"Eng. Appl. Artif. Intell."},{"issue":"1","key":"10.1016\/j.asoc.2026.115093_bib0020","doi-asserted-by":"crossref","first-page":"535","DOI":"10.1146\/annurev-control-071020-045021","article-title":"Dynamic walking: toward agile and efficient bipedal robots","volume":"4","author":"Reher","year":"2021","journal-title":"Annu. Rev. Control Robot. Auton. Syst."},{"key":"10.1016\/j.asoc.2026.115093_bib0025","article-title":"Whole-body constrained learning for legged locomotion via hierarchical optimization","author":"Wang","year":"2025","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.asoc.2026.115093_bib0030","author":"Makoviychuk"},{"key":"10.1016\/j.asoc.2026.115093_bib0035","series-title":"IEEE International Conference on Robotics and Automation (ICRA)","first-page":"2811","article-title":"Reinforcement learning for robust parameterized locomotion control","author":"Xie","year":"2020"},{"issue":"8","key":"10.1016\/j.asoc.2026.115093_bib0040","doi-asserted-by":"crossref","first-page":"6750","DOI":"10.1109\/TIE.2020.3001845","article-title":"Model-based and model-free control of dc\u2013dc converters with high-order dynamics and limited measurements","volume":"68","author":"Loranca-Coutino","year":"2020","journal-title":"IEEE Trans. Ind. Electron."},{"key":"10.1016\/j.asoc.2026.115093_bib0045","doi-asserted-by":"crossref","DOI":"10.1016\/j.aei.2024.102960","article-title":"Cooperative dual-actor proximal policy optimization algorithm for multi-robot complex control task","volume":"63","author":"Baltes","year":"2025","journal-title":"Adv. Eng. Inform."},{"key":"10.1016\/j.asoc.2026.115093_bib0050","doi-asserted-by":"crossref","DOI":"10.1016\/j.asoc.2021.107601","article-title":"Hierarchical deep reinforcement learning to drag heavy objects by adult-sized humanoid robot","volume":"110","author":"Saeedvand","year":"2021","journal-title":"Appl. Soft Comput."},{"key":"10.1016\/j.asoc.2026.115093_bib0055","series-title":"2016 IEEE-RAS 16th International Conference on Humanoid Robots (Humanoids)","first-page":"938","article-title":"Open source integrated 3d footstep planning framework for humanoid robots","author":"Stumpf","year":"2016"},{"issue":"3","key":"10.1016\/j.asoc.2026.115093_bib0060","doi-asserted-by":"crossref","first-page":"283","DOI":"10.1016\/S0921-8890(97)00043-2","article-title":"Biped dynamic walking using reinforcement learning","volume":"22","author":"Benbrahim","year":"1997","journal-title":"Robot. Auton. Syst."},{"key":"10.1016\/j.asoc.2026.115093_bib0065","doi-asserted-by":"crossref","first-page":"1054","DOI":"10.1109\/TNN.1998.712192","article-title":"Reinforcement learning: an introduction","volume":"9","author":"Sutton","year":"1998","journal-title":"IEEE Trans. Neural Netw."},{"key":"10.1016\/j.asoc.2026.115093_bib0070","doi-asserted-by":"crossref","first-page":"94","DOI":"10.1016\/j.neucom.2023.02.008","article-title":"Improving proximal policy optimization with alpha divergence","volume":"534","author":"Xu","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.asoc.2026.115093_bib0075","doi-asserted-by":"crossref","first-page":"750","DOI":"10.1016\/j.ins.2022.07.111","article-title":"Proximal policy optimization via enhanced exploration efficiency","volume":"609","author":"Zhang","year":"2022","journal-title":"Inf. Sci."},{"key":"10.1016\/j.asoc.2026.115093_bib0080","series-title":"A Biped Robot Learning to Walk Like Human by Reinforcement Learning","author":"Liu","year":"2023"},{"key":"10.1016\/j.asoc.2026.115093_bib0085","series-title":"Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor","author":"Haarnoja","year":"2018"},{"issue":"5","key":"10.1016\/j.asoc.2026.115093_bib0090","doi-asserted-by":"crossref","first-page":"8577","DOI":"10.1109\/JIOT.2019.2921159","article-title":"Deep deterministic policy gradient (DDPG)-based energy harvesting wireless communications","volume":"6","author":"Qiu","year":"2019","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.asoc.2026.115093_bib0095","series-title":"Twin-Delayed Ddpg: A Deep Reinforcement Learning Technique to Model a Continuous Movement of an Intelligent Robot Agent","author":"Dankwa","year":"2020"},{"key":"10.1016\/j.asoc.2026.115093_bib0100","unstructured":"Robotis, Introduction, https:\/\/emanual.robotis.com\/docs\/en\/platform\/op3\/introduction\/"},{"key":"10.1016\/j.asoc.2026.115093_bib0105","first-page":"21235","article-title":"Stochastic latent actor-critic: deep reinforcement learning with a latent variable model","volume":"33","author":"Lee","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"8","key":"10.1016\/j.asoc.2026.115093_bib0110","doi-asserted-by":"crossref","DOI":"10.3390\/biomimetics8080616","article-title":"A multi-agent reinforcement learning method for omnidirectional walking of bipedal robots","volume":"8","author":"Mou","year":"2023","journal-title":"Biomimetics"},{"key":"10.1016\/j.asoc.2026.115093_bib0115","series-title":"Dynamic Walking in a Humanoid Robot Based on a 3d Actuated Dual-Slip Model","first-page":"5710","author":"Liu","year":"2015"},{"key":"10.1016\/j.asoc.2026.115093_bib0120","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1016\/j.procs.2015.12.052","article-title":"Trajectory generation using predictive PID control for stable walking humanoid robot","volume":"73","author":"Bouhajar","year":"2015","journal-title":"Proc. Comput. Sci."},{"issue":"3","key":"10.1016\/j.asoc.2026.115093_bib0125","doi-asserted-by":"crossref","first-page":"335","DOI":"10.1016\/0005-1098(89)90002-2","article-title":"Model predictive control: theory and practice\u2014a survey","volume":"25","author":"Garc\u00eda","year":"1989","journal-title":"Automatica"},{"key":"10.1016\/j.asoc.2026.115093_bib0130","first-page":"239","article-title":"The 3D Linear Inverted Pendulum Mode: A Simple Modeling for a Biped Walking Pattern Generation","volume":"Vol. 1","author":"Kajita","year":"2001"},{"key":"10.1016\/j.asoc.2026.115093_bib0135","series-title":"Online Walking Gait Generation with Adaptive Foot Positioning Through Linear Model Predictive Control","first-page":"1121","author":"Diedam","year":"2008"},{"key":"10.1016\/j.asoc.2026.115093_bib0140","doi-asserted-by":"crossref","DOI":"10.1007\/s10514-013-9341-4","article-title":"Centroidal dynamics of a humanoid robot","volume":"35","author":"Orin","year":"2013","journal-title":"Auton. Robots."},{"key":"10.1016\/j.asoc.2026.115093_bib0145","series-title":"Robust Dynamic Walking Using Online Foot Step Optimization","first-page":"5373","author":"Feng","year":"2016"},{"key":"10.1016\/j.asoc.2026.115093_bib0150","series-title":"Multi-Task Control for a Quadruped Robot with Changeable Leg Configuration","first-page":"3944","author":"Ye","year":"2020"},{"issue":"1","key":"10.1016\/j.asoc.2026.115093_bib0155","doi-asserted-by":"crossref","DOI":"10.3390\/electronics13010116","article-title":"Automated hyperparameter tuning in reinforcement learning for quadrupedal robot locomotion","volume":"13","author":"Kim","year":"2024","journal-title":"Electronics"},{"key":"10.1016\/j.asoc.2026.115093_bib0160","author":"Li"},{"key":"10.1016\/j.asoc.2026.115093_bib0165","author":"Schulman"},{"key":"10.1016\/j.asoc.2026.115093_bib0170","author":"Lillicrap"},{"key":"10.1016\/j.asoc.2026.115093_bib0175","series-title":"IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)","first-page":"16","article-title":"Curiosity-driven exploration by self-supervised prediction","author":"Pathak","year":"2017"},{"key":"10.1016\/j.asoc.2026.115093_bib0180","series-title":"International Conference on Learning Representations (ICLR)","article-title":"Parameter space noise for exploration","author":"Plappert","year":"2018"},{"key":"10.1016\/j.asoc.2026.115093_bib0185","series-title":"Advances in Neural Information Processing Systems (NeurIPS)","article-title":"Deep exploration via bootstrapped DQN","volume":"vol. 29","author":"Osband","year":"2016"},{"key":"10.1016\/j.asoc.2026.115093_bib0190","series-title":"Proceedings of the 2017 AAAI Conference on Artificial Intelligence","article-title":"Emergence of locomotion behaviours in rich environments","author":"Heess","year":"2017"},{"key":"10.1016\/j.asoc.2026.115093_bib0195","author":"Kumar"},{"key":"10.1016\/j.asoc.2026.115093_bib0200","series-title":"2022 International Conference on Robotics and Automation (ICRA)","first-page":"10449","article-title":"Sim-to-real learning for bipedal locomotion under unsensed dynamic loads","author":"Dao","year":"2022"},{"key":"10.1016\/j.asoc.2026.115093_bib0205","series-title":"Computer Graphics Forum","first-page":"213","article-title":"Allsteps: curriculum-driven learning of stepping stone skills","volume":"vol. 39","author":"Xie","year":"2020"},{"key":"10.1016\/j.asoc.2026.115093_bib0210","series-title":"Learning Bipedal Walking on Planned Footsteps for Humanoid Robots","author":"Singh","year":"2022"},{"key":"10.1016\/j.asoc.2026.115093_bib0215","series-title":"ACM Transactions on Graphics (TOG)","first-page":"143:1","article-title":"Deepmimic: example-guided Deep reinforcement learning of physics-based character skills","volume":"vol. 37","author":"Peng","year":"2018"},{"issue":"26","key":"10.1016\/j.asoc.2026.115093_bib0220","doi-asserted-by":"crossref","DOI":"10.1126\/scirobotics.aau5872","article-title":"Learning agile and dynamic motor skills for legged robots","volume":"4","author":"Hwangbo","year":"2019","journal-title":"Sci. Robot."},{"key":"10.1016\/j.asoc.2026.115093_bib0225","series-title":"IEEE Robotics and Automation Letters (RA-L)","first-page":"1993","article-title":"Learning fast adaptation with meta strategy optimization","volume":"vol. 3","author":"Yu","year":"2018"},{"key":"10.1016\/j.asoc.2026.115093_bib0230","series-title":"SIGGRAPH Asia 2021 Conference Papers","article-title":"Learning agile robotic locomotion skills by imitating animals","author":"Peng","year":"2021"},{"issue":"9","key":"10.1016\/j.asoc.2026.115093_bib0235","doi-asserted-by":"crossref","first-page":"4364","DOI":"10.1109\/TAI.2024.3379969","article-title":"Enhancing reinforcement learning via transformer-based state predictive representations","volume":"5","author":"Liu","year":"2024","journal-title":"IEEE Trans. Artif. Intell."},{"issue":"12","key":"10.1016\/j.asoc.2026.115093_bib0240","doi-asserted-by":"crossref","first-page":"12698","DOI":"10.1109\/TCYB.2021.3086501","article-title":"Learning to optimize: reference vector reinforcement learning adaption to constrained many-objective optimization of industrial copper burdening system","volume":"52","author":"Ma","year":"2021","journal-title":"IEEE Trans. Cybern."},{"issue":"7","key":"10.1016\/j.asoc.2026.115093_bib0245","doi-asserted-by":"crossref","first-page":"6684","DOI":"10.1109\/TCYB.2020.3041212","article-title":"An adaptive localized decision variable analysis approach to large-scale multiobjective and many-objective optimization","volume":"52","author":"Ma","year":"2022","journal-title":"IEEE Trans. Cybern."},{"issue":"12","key":"10.1016\/j.asoc.2026.115093_bib0250","doi-asserted-by":"crossref","first-page":"21350","DOI":"10.1109\/JIOT.2025.3546915","article-title":"Multiagent deep-reinforcement-learning-based cooperative perception and computation in VEC","volume":"12","author":"Zhao","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.asoc.2026.115093_bib0255","author":"Hendrycks"},{"key":"10.1016\/j.asoc.2026.115093_bib0260","series-title":"International Conference on Machine Learning","first-page":"1587","article-title":"Addressing function approximation error in actor-critic methods","author":"Fujimoto","year":"2018"}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626005417?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494626005417?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,23]],"date-time":"2026-05-23T23:34:24Z","timestamp":1779579264000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494626005417"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":52,"alternative-id":["S1568494626005417"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115093","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A dual-actor proximal policy optimization algorithm for humanoid robot navigation control","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2026.115093","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":"115093"}}