{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T11:23:02Z","timestamp":1783164182843,"version":"3.54.6"},"reference-count":60,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100006606","name":"Natural Science Foundation of Tianjin Municipality","doi-asserted-by":"publisher","award":["25JCZDJC00580"],"award-info":[{"award-number":["25JCZDJC00580"]}],"id":[{"id":"10.13039\/501100006606","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24B2047"],"award-info":[{"award-number":["U24B2047"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["52575033"],"award-info":[{"award-number":["52575033"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Engineering Applications of Artificial Intelligence"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.engappai.2026.115297","type":"journal-article","created":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T16:23:05Z","timestamp":1780676585000},"page":"115297","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"P1","title":["Hierarchical multi-policy adversarial reinforcement learning"],"prefix":"10.1016","volume":"181","author":[{"given":"Xiaofeng","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaopu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9638-2741","authenticated-orcid":false,"given":"Jipeng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yue","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.engappai.2026.115297_b1","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1613\/jair.731","article-title":"A model of inductive bias learning","volume":"12","author":"Baxter","year":"2000","journal-title":"J. Artificial Intelligence Res."},{"key":"10.1016\/j.engappai.2026.115297_b2","doi-asserted-by":"crossref","unstructured":"Bengio, Yoshua, Louradour, J\u00e9r\u00f4me, Collobert, Ronan, Weston, Jason, 2009. Curriculum learning. In: Proceedings of the 26th Annual International Conference on Machine Learning. pp. 41\u201348.","DOI":"10.1145\/1553374.1553380"},{"key":"10.1016\/j.engappai.2026.115297_b3","series-title":"Dota 2 with large scale deep reinforcement learning","author":"Berner","year":"2019"},{"key":"10.1016\/j.engappai.2026.115297_b4","series-title":"Controlling behavioral diversity in multi-agent reinforcement learning","author":"Bettini","year":"2024"},{"key":"10.1016\/j.engappai.2026.115297_b5","series-title":"The impact of behavioral diversity in multi-agent reinforcement learning","author":"Bettini","year":"2024"},{"key":"10.1016\/j.engappai.2026.115297_b6","series-title":"Trajectory first: A curriculum for discovering diverse policies","author":"Braun","year":"2025"},{"key":"10.1016\/j.engappai.2026.115297_b7","doi-asserted-by":"crossref","unstructured":"Cao, Zhe, Simon, Tomas, Wei, Shih-En, Sheikh, Yaser, 2017. Realtime multi-person 2d pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7291\u20137299.","DOI":"10.1109\/CVPR.2017.143"},{"issue":"1","key":"10.1016\/j.engappai.2026.115297_b8","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1023\/A:1007379606734","article-title":"Multitask learning","volume":"28","author":"Caruana","year":"1997","journal-title":"Mach. Learn."},{"key":"10.1016\/j.engappai.2026.115297_b9","series-title":"Understanding domain randomization for sim-to-real transfer","author":"Chen","year":"2021"},{"key":"10.1016\/j.engappai.2026.115297_b10","doi-asserted-by":"crossref","first-page":"123353","DOI":"10.52202\/079017-3921","article-title":"Difflight: a partial rewards conditioned diffusion model for traffic signal control with missing data","volume":"37","author":"Chen","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1","key":"10.1016\/j.engappai.2026.115297_b11","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1007\/s44196-025-00875-8","article-title":"Risk-adjusted deep reinforcement learning for portfolio optimization: A multi-reward approach","volume":"18","author":"Choudhary","year":"2025","journal-title":"Int. J. Comput. Intell. Syst."},{"key":"10.1016\/j.engappai.2026.115297_b12","series-title":"European Conference on Computer Vision","first-page":"374","article-title":"Domain randomization-enhanced depth simulation and restoration for perceiving and grasping specular and transparent objects","author":"Dai","year":"2022"},{"key":"10.1016\/j.engappai.2026.115297_b13","doi-asserted-by":"crossref","unstructured":"Dong, Xiaoyi, Bao, Jianmin, Chen, Dongdong, Zhang, Weiming, Yu, Nenghai, Yuan, Lu, Chen, Dong, Guo, Baining, 2022. Cswin transformer: A general vision transformer backbone with cross-shaped windows. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 12124\u201312134.","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"10.1016\/j.engappai.2026.115297_b14","series-title":"Diversity is all you need: Learning skills without a reward function","author":"Eysenbach","year":"2018"},{"key":"10.1016\/j.engappai.2026.115297_b15","series-title":"Adversarial environment generation for learning to navigate the web","author":"Gur","year":"2021"},{"key":"10.1016\/j.engappai.2026.115297_b16","series-title":"Soft actor-critic algorithms and applications","author":"Haarnoja","year":"2018"},{"key":"10.1016\/j.engappai.2026.115297_b17","doi-asserted-by":"crossref","unstructured":"He, Kaiming, Gkioxari, Georgia, Doll\u00e1r, Piotr, Girshick, Ross, 2017. Mask r-cnn. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 2961\u20132969.","DOI":"10.1109\/ICCV.2017.322"},{"key":"10.1016\/j.engappai.2026.115297_b18","article-title":"Deep reinforcement learning that matters","volume":"vol. 32","author":"Henderson","year":"2018"},{"key":"10.1016\/j.engappai.2026.115297_b19","doi-asserted-by":"crossref","unstructured":"Hestness, Joel, Ardalani, Newsha, Diamos, Gregory, 2019. Beyond human-level accuracy: Computational challenges in deep learning. In: Proceedings of the 24th Symposium on Principles and Practice of Parallel Programming. pp. 1\u201314.","DOI":"10.1145\/3293883.3295710"},{"key":"10.1016\/j.engappai.2026.115297_b20","series-title":"2024 IEEE International Conference on Robotics and Automation","first-page":"18355","article-title":"Uncertainty-aware reinforcement learning for autonomous driving with multimodal digital driver guidance","author":"Huang","year":"2024"},{"key":"10.1016\/j.engappai.2026.115297_b21","doi-asserted-by":"crossref","DOI":"10.1016\/j.gfj.2024.101016","article-title":"Deep reinforcement learning for portfolio selection","volume":"62","author":"Jiang","year":"2024","journal-title":"Glob. Financ. J."},{"key":"10.1016\/j.engappai.2026.115297_b22","doi-asserted-by":"crossref","first-page":"8906","DOI":"10.1109\/TMM.2023.3243616","article-title":"Dilateformer: Multi-scale dilated transformer for visual recognition","volume":"25","author":"Jiao","year":"2023","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.engappai.2026.115297_b23","series-title":"Curriculum learning with counterfactual group relative policy advantage for multi-agent reinforcement learning","author":"Jin","year":"2025"},{"key":"10.1016\/j.engappai.2026.115297_b24","doi-asserted-by":"crossref","unstructured":"Kendall, Alex, Gal, Yarin, Cipolla, Roberto, 2018. Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7482\u20137491.","DOI":"10.1109\/CVPR.2018.00781"},{"key":"10.1016\/j.engappai.2026.115297_b25","series-title":"2024 IEEE International Conference on Robotics and Automation","first-page":"8239","article-title":"AD4rl: Autonomous driving benchmarks for offline reinforcement learning with value-based dataset","author":"Lee","year":"2024"},{"key":"10.1016\/j.engappai.2026.115297_b26","series-title":"The choice of divergence: A neglected key to mitigating diversity collapse in reinforcement learning with verifiable reward","author":"Li","year":"2025"},{"key":"10.1016\/j.engappai.2026.115297_b27","doi-asserted-by":"crossref","first-page":"38456","DOI":"10.52202\/079017-1214","article-title":"Learning multimodal behaviors from scratch with diffusion policy gradient","volume":"37","author":"Li","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"3","key":"10.1016\/j.engappai.2026.115297_b28","doi-asserted-by":"crossref","first-page":"3461","DOI":"10.1109\/TPAMI.2022.3190471","article-title":"Metadrive: Composing diverse driving scenarios for generalizable reinforcement learning","volume":"45","author":"Li","year":"2022","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.engappai.2026.115297_b29","first-page":"3991","article-title":"Celebrating diversity in shared multi-agent reinforcement learning","volume":"34","author":"Li","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115297_b30","series-title":"Towards optimal adversarial robust reinforcement learning with infinity measurement error","author":"Li","year":"2025"},{"key":"10.1016\/j.engappai.2026.115297_b31","series-title":"Vendirl: A framework for self-supervised reinforcement learning of diversely diverse skills","author":"Lintunen","year":"2025"},{"key":"10.1016\/j.engappai.2026.115297_b32","doi-asserted-by":"crossref","unstructured":"Liu, Ze, Lin, Yutong, Cao, Yue, Hu, Han, Wei, Yixuan, Zhang, Zheng, Lin, Stephen, Guo, Baining, 2021. Swin transformer: Hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 10012\u201310022.","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"10.1016\/j.engappai.2026.115297_b33","series-title":"Conference on Robot Learning","first-page":"1162","article-title":"Active domain randomization","author":"Mehta","year":"2020"},{"issue":"2","key":"10.1016\/j.engappai.2026.115297_b34","doi-asserted-by":"crossref","first-page":"911","DOI":"10.1109\/LRA.2021.3052391","article-title":"Data-efficient domain randomization with bayesian optimization","volume":"6","author":"Muratore","year":"2021","journal-title":"IEEE Robot. Autom. Lett."},{"key":"10.1016\/j.engappai.2026.115297_b35","series-title":"Finding the pillars of strength for multi-head attention","author":"Ni","year":"2023"},{"key":"10.1016\/j.engappai.2026.115297_b36","series-title":"2019 International Conference on Robotics and Automation","first-page":"8522","article-title":"Risk averse robust adversarial reinforcement learning","author":"Pan","year":"2019"},{"issue":"4","key":"10.1016\/j.engappai.2026.115297_b37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3450626.3459670","article-title":"Amp: Adversarial motion priors for stylized physics-based character control","volume":"40","author":"Peng","year":"2021","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"10.1016\/j.engappai.2026.115297_b38","series-title":"International Conference on Machine Learning","first-page":"2817","article-title":"Robust adversarial reinforcement learning","author":"Pinto","year":"2017"},{"key":"10.1016\/j.engappai.2026.115297_b39","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.107981","article-title":"Refine to the essence: Less-redundant skill learning via diversity clustering","volume":"133","author":"Qing","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.115297_b40","series-title":"Vehicle dynamics and control","isbn-type":"print","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-4614-1433-9","author":"Rajamani","year":"2012","ISBN":"https:\/\/id.crossref.org\/isbn\/9781461414339"},{"key":"10.1016\/j.engappai.2026.115297_b41","article-title":"Faster r-cnn: Towards real-time object detection with region proposal networks","volume":"28","author":"Ren","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115297_b42","series-title":"Poutine: Vision-language-trajectory pre-training and reinforcement learning post-training enable robust end-to-end autonomous driving","author":"Rowe","year":"2025"},{"key":"10.1016\/j.engappai.2026.115297_b43","series-title":"cMALC-d: Contextual multi-agent LLM-guided curriculum learning with diversity-based context blending","author":"Satheesh","year":"2025"},{"key":"10.1016\/j.engappai.2026.115297_b44","series-title":"Proximal policy optimization algorithms","author":"Schulman","year":"2017"},{"issue":"5","key":"10.1016\/j.engappai.2026.115297_b45","doi-asserted-by":"crossref","first-page":"2815","DOI":"10.3390\/app15052815","article-title":"Policy similarity measure for two-player zero-sum games","volume":"15","author":"Tang","year":"2025","journal-title":"Appl. Sci."},{"key":"10.1016\/j.engappai.2026.115297_b46","series-title":"2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems","first-page":"23","article-title":"Domain randomization for transferring deep neural networks from simulation to the real world","author":"Tobin","year":"2017"},{"key":"10.1016\/j.engappai.2026.115297_b47","series-title":"Robust reinforcement learning using adversarial populations","author":"Vinitsky","year":"2020"},{"key":"10.1016\/j.engappai.2026.115297_b48","first-page":"20","article-title":"Alphastar: Mastering the real-time strategy game starcraft ii","volume":"2","author":"Vinyals","year":"2019","journal-title":"Deep. Blog"},{"issue":"7782","key":"10.1016\/j.engappai.2026.115297_b49","doi-asserted-by":"crossref","first-page":"350","DOI":"10.1038\/s41586-019-1724-z","article-title":"Grandmaster level in StarCraft II using multi-agent reinforcement learning","volume":"575","author":"Vinyals","year":"2019","journal-title":"Nature"},{"key":"10.1016\/j.engappai.2026.115297_b50","series-title":"How to pick the domain randomization parameters for sim-to-real transfer of reinforcement learning policies?","author":"Vuong","year":"2019"},{"issue":"9","key":"10.1016\/j.engappai.2026.115297_b51","first-page":"4555","article-title":"A survey on curriculum learning","volume":"44","author":"Wang","year":"2021","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.engappai.2026.115297_b52","first-page":"1","article-title":"Diversity-enhanced conversational recommendation via multi-agent reinforcement learning","author":"Wang","year":"2025","journal-title":"Knowl. Inf. Syst."},{"key":"10.1016\/j.engappai.2026.115297_b53","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2023.107728","article-title":"Adversarial deep reinforcement learning based robust depth tracking control for underactuated autonomous underwater vehicle","volume":"130","author":"Wang","year":"2024","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.115297_b54","doi-asserted-by":"crossref","first-page":"94073","DOI":"10.52202\/079017-2984","article-title":"Multi-head mixture-of-experts","volume":"37","author":"Wu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.engappai.2026.115297_b55","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.109726","article-title":"Train a real-world local path planner in one hour via partially decoupled reinforcement learning and vectorized diversity","volume":"141","author":"Xin","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.engappai.2026.115297_b56","article-title":"PPO-act: Proximal policy optimization with adversarial curriculum transfer for spatial public goods games","volume":"199","author":"Yang","year":"2025","journal-title":"Chaos Solitons Fractals"},{"key":"10.1016\/j.engappai.2026.115297_b57","unstructured":"Yu, Tianhe, Kumar, Saurabh, Gupta, Abhishek, Levine, Sergey, Hausman, Karol, Finn, Chelsea, 2019. Multi-task reinforcement learning without interference. In: Proc. Optim. Found. Reinforcement Learn. Workshop NeurIPS."},{"key":"10.1016\/j.engappai.2026.115297_b58","first-page":"10571","article-title":"Robust multi-agent reinforcement learning with model uncertainty","volume":"33","author":"Zhang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"1","key":"10.1016\/j.engappai.2026.115297_b59","doi-asserted-by":"crossref","first-page":"8286","DOI":"10.1038\/s41598-025-93175-2","article-title":"Deep reinforcement learning trajectory planning for robotic manipulator based on simulation-efficient training","volume":"15","author":"Zhao","year":"2025","journal-title":"Sci. Rep."},{"key":"10.1016\/j.engappai.2026.115297_b60","series-title":"Continuous control reinforcement learning: distributed distributional DrQ algorithms","author":"Zhou","year":"2024"}],"container-title":["Engineering Applications of Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626015812?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0952197626015812?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T11:08:33Z","timestamp":1783163313000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0952197626015812"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":60,"alternative-id":["S0952197626015812"],"URL":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115297","relation":{},"ISSN":["0952-1976"],"issn-type":[{"value":"0952-1976","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Hierarchical multi-policy adversarial reinforcement learning","name":"articletitle","label":"Article Title"},{"value":"Engineering Applications of Artificial Intelligence","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.engappai.2026.115297","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"115297"}}