{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T08:22:18Z","timestamp":1774858938737,"version":"3.50.1"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T00:00:00Z","timestamp":1769817600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T00:00:00Z","timestamp":1770768000000},"content-version":"vor","delay-in-days":11,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Intell Robot Syst"],"DOI":"10.1007\/s10846-026-02360-6","type":"journal-article","created":{"date-parts":[[2026,1,31]],"date-time":"2026-01-31T08:14:45Z","timestamp":1769847285000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Agent Continual Deep Reinforcement Learning with Artificial Potential Fields and Switching Control for a Cooperative Robotic Task"],"prefix":"10.1007","volume":"112","author":[{"given":"Wenbo","family":"Tan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Lv","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"XiangQing","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Na","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Na","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,1,31]]},"reference":[{"key":"2360_CR1","doi-asserted-by":"publisher","unstructured":"Mohamed, S.A., Mahmoud, M.A., Mahdi, M.N., Mostafa, S.A.: Improving efficiency and effectiveness of robotic process automation in human resource management. Sustainability. 14, 3920 (2022). https:\/\/doi.org\/10.3390\/su14073920","DOI":"10.3390\/su14073920"},{"key":"2360_CR2","doi-asserted-by":"publisher","unstructured":"Luo, L.: An improved a* algorithm for agv path planning. In: 2023 IEEE international conference on image processing and computer applications (ICIPCA), pp. 739\u2013743 (2023). https:\/\/doi.org\/10.1109\/ICIPCA59209.2023.10257733. IEEE","DOI":"10.1109\/ICIPCA59209.2023.10257733"},{"key":"2360_CR3","doi-asserted-by":"publisher","unstructured":"Chen, X., Liu, S., Zhao, J., Wu, H., Xian, J., Montewka, J.: Autonomous port management based agv path planning and optimization via an ensemble reinforcement learning framework. Ocean Coast. Manag. 251, 107087 (2024). https:\/\/doi.org\/10.1016\/j.ocecoaman.2024.107087","DOI":"10.1016\/j.ocecoaman.2024.107087"},{"key":"2360_CR4","doi-asserted-by":"publisher","unstructured":"Chiu, Z.-Y., Richter, F., Funk, E.K., Orosco, R.K., Yip, M.C.: Bimanual regrasping for suture needles using reinforcement learning for rapid motion planning. In: 2021 IEEE international conference on robotics and automation (ICRA), pp. 7737\u20137743 (2021). https:\/\/doi.org\/10.1109\/ICRA48506.2021.9561673. IEEE","DOI":"10.1109\/ICRA48506.2021.9561673"},{"issue":"10","key":"2360_CR5","doi-asserted-by":"publisher","first-page":"5204","DOI":"10.3390\/app12105204","volume":"12","author":"Y Wang","year":"2022","unstructured":"Wang, Y., Wang, L., Zhao, Y.: Research on door opening operation of mobile robotic arm based on reinforcement learning. Appl. Sci. 12(10), 5204 (2022). https:\/\/doi.org\/10.3390\/app12105204","journal-title":"Appl. Sci."},{"key":"2360_CR6","doi-asserted-by":"publisher","unstructured":"Tan, H.: Reinforcement learning with deep deterministic policy gradient. In: 2021 international conference on artificial intelligence, big data and algorithms (CAIBDA), pp. 82\u201385 (2021). https:\/\/doi.org\/10.1109\/CAIBDA53561.2021.00025. IEEE","DOI":"10.1109\/CAIBDA53561.2021.00025"},{"key":"2360_CR7","doi-asserted-by":"publisher","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint. (2017). https:\/\/doi.org\/10.48550\/arXiv.1707.06347","DOI":"10.48550\/arXiv.1707.06347"},{"key":"2360_CR8","doi-asserted-by":"publisher","unstructured":"Haarnoja, T., Zhou, A., Hartikainen, K., Tucker, G., Ha, S., Tan, J., Kumar, V., Zhu, H., Gupta, A., Abbeel, P., et al.: Soft actor-critic algorithms and applications. arXiv preprint. (2018). https:\/\/doi.org\/10.48550\/arXiv.1812.05905","DOI":"10.48550\/arXiv.1812.05905"},{"issue":"3\u20134","key":"2360_CR9","doi-asserted-by":"publisher","first-page":"2182","DOI":"10.1002\/cav.2182","volume":"34","author":"X Shang","year":"2023","unstructured":"Shang, X., Xu, T., Karamouzas, I., Kallmann, M.: Constraint-based multi-agent reinforcement learning for collaborative tasks. Comput. Animat. Virtual Worlds. 34(3\u20134), 2182 (2023). https:\/\/doi.org\/10.1002\/cav.2182","journal-title":"Comput. Animat. Virtual Worlds."},{"issue":"11","key":"2360_CR10","doi-asserted-by":"publisher","first-page":"13677","DOI":"10.1007\/s10489-022-04105-y","volume":"53","author":"A Oroojlooy","year":"2023","unstructured":"Oroojlooy, A., Hajinezhad, D.: A review of cooperative multi-agent deep reinforcement learning. Appl. Intell. 53(11), 13677\u201313722 (2023). https:\/\/doi.org\/10.1007\/s10489-022-04105-y","journal-title":"Appl. Intell."},{"key":"2360_CR11","doi-asserted-by":"publisher","unstructured":"Da\u00a0Silva, F.L., Costa, A.H.R.: A survey on transfer learning for multiagent reinforcement learning systems. J. Artif. Intell. Res. 64, 645\u2013703 (2019). https:\/\/doi.org\/10.1613\/jair.1.11396","DOI":"10.1613\/jair.1.11396"},{"key":"2360_CR12","doi-asserted-by":"publisher","unstructured":"Cui, Y., Xu, Z., Zhong, L., Xu, P., Shen, Y., Tang, Q.: A task-adaptive deep reinforcement learning framework for dual-arm robot manipulation. IEEE Trans. Autom. Sci. Eng. 22, 466\u2013479 (2024). https:\/\/doi.org\/10.1109\/TASE.2024.3352584","DOI":"10.1109\/TASE.2024.3352584"},{"issue":"2","key":"2360_CR13","doi-asserted-by":"publisher","first-page":"1240","DOI":"10.1109\/COMST.2022.3160697","volume":"24","author":"T Li","year":"2022","unstructured":"Li, T., Zhu, K., Luong, N.C., Niyato, D., Wu, Q., Zhang, Y., Chen, B.: Applications of multi-agent reinforcement learning in future internet: A comprehensive survey. IEEE Commun. Surv. Tutor. 24(2), 1240\u20131279 (2022). https:\/\/doi.org\/10.1109\/COMST.2022.3160697","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"2360_CR14","doi-asserted-by":"publisher","unstructured":"Zhang, D., Chen, C., Zhang, G.: Agv path planning based on improved a-star algorithm. In: 2024 IEEE 7th advanced information technology, electronic and automation control conference (IAEAC), vol. 7, pp. 1590\u20131595 (2024). https:\/\/doi.org\/10.1109\/IAEAC59436.2024.10503919. IEEE","DOI":"10.1109\/IAEAC59436.2024.10503919"},{"key":"2360_CR15","doi-asserted-by":"publisher","unstructured":"Chen, X., Liu, S., Zhao, J., Wu, H., Xian, J., Montewka, J.: Autonomous port management based agv path planning and optimization via an ensemble reinforcement learning framework. Ocean Coast. Manag. 251, 107087 (2024). https:\/\/doi.org\/10.1016\/j.ocecoaman.2024.107087","DOI":"10.1016\/j.ocecoaman.2024.107087"},{"key":"2360_CR16","doi-asserted-by":"publisher","unstructured":"Warren, C.W.: Global path planning using artificial potential fields. In: 1989 IEEE international conference on robotics and automation, pp. 316\u2013317 (1989). https:\/\/doi.org\/10.1109\/ROBOT.1989.100007 . IEEE Computer Society","DOI":"10.1109\/ROBOT.1989.100007"},{"key":"2360_CR17","doi-asserted-by":"publisher","unstructured":"Chi, C., Xu, Z., Feng, S., Cousineau, E., Du, Y., Burchfiel, B., Tedrake, R., Song, S.: Diffusion policy: Visuomotor policy learning via action diffusion. Intl. J. Robot. Res. 02783649241273668 (2023). https:\/\/doi.org\/10.1177\/02783649241273","DOI":"10.1177\/02783649241273"},{"key":"2360_CR18","unstructured":"Song, J., Ren, H., Sadigh, D., Ermon, S.: Multi-agent generative adversarial imitation learning. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"issue":"1","key":"2360_CR19","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1177\/027836498600500106","volume":"5","author":"O Khatib","year":"1986","unstructured":"Khatib, O.: Real-time obstacle avoidance for manipulators and mobile robots. The international journal of robotics research. 5(1), 90\u201398 (1986). https:\/\/doi.org\/10.1177\/027836498600500106","journal-title":"The international journal of robotics research."},{"issue":"8","key":"2360_CR20","doi-asserted-by":"publisher","first-page":"11393","DOI":"10.1007\/s10586-024-04287-9","volume":"27","author":"Y Yang","year":"2024","unstructured":"Yang, Y., Luo, X., Li, W., Liu, C., Ye, Q., Liang, P.: Aapf*: A safer autonomous vehicle path planning algorithm based on the improved a* algorithm and apf algorithm. Clust. Comput. 27(8), 11393\u201311406 (2024). https:\/\/doi.org\/10.1007\/s10586-024-04287-9","journal-title":"Clust. Comput."},{"issue":"1","key":"2360_CR21","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/JRA.1987.1087068","volume":"3","author":"O Khatib","year":"1987","unstructured":"Khatib, O.: A unified approach for motion and force control of robot manipulators: The operational space formulation. IEEE J. Robot. Autom. 3(1), 43\u201353 (1987). https:\/\/doi.org\/10.1109\/JRA.1987.1087068","journal-title":"IEEE J. Robot. Autom."},{"issue":"1","key":"2360_CR22","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1007\/BF01254007","volume":"14","author":"AS Deo","year":"1995","unstructured":"Deo, A.S., Walker, I.D.: Overview of damped least-squares methods for inverse kinematics of robot manipulators. J. Intell. Rob. Syst. 14(1), 43\u201368 (1995). https:\/\/doi.org\/10.1007\/BF01254007","journal-title":"J. Intell. Rob. Syst."},{"issue":"3","key":"2360_CR23","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1109\/70.585902","volume":"13","author":"S Chiaverini","year":"1997","unstructured":"Chiaverini, S.: Singularity-robust task-priority redundancy resolution for real-time kinematic control of robot manipulators. IEEE Trans. Robot. Autom. 13(3), 398\u2013410 (1997). https:\/\/doi.org\/10.1109\/70.585902","journal-title":"IEEE Trans. Robot. Autom."},{"issue":"23","key":"2360_CR24","doi-asserted-by":"publisher","first-page":"9617","DOI":"10.3390\/s23239617","volume":"23","author":"X Wang","year":"2023","unstructured":"Wang, X., Wu, Q., Wang, T., Cui, Y.: A path-planning method to significantly reduce local oscillation of manipulators based on velocity potential field. Sensors. 23(23), 9617 (2023). https:\/\/doi.org\/10.3390\/s23239617","journal-title":"Sensors."},{"issue":"14","key":"2360_CR25","doi-asserted-by":"publisher","first-page":"4370","DOI":"10.3390\/s25144370","volume":"25","author":"Y Li","year":"2025","unstructured":"Li, Y., Yang, Y., Liu, K., Wen, C.-Y.: Intelligent joint space path planning: Enhancing motion feasibility with goal-driven and potential field strategies. Sensors. 25(14), 4370 (2025). https:\/\/doi.org\/10.3390\/s25144370","journal-title":"Sensors."},{"key":"2360_CR26","doi-asserted-by":"publisher","unstructured":"He, C., Lian, S., Shi, Q., Miao, Z.: An improved joint space a* algorithm for a 6-dof manipulator with pre-planning strategy. Sci. Rep. 15, 18164 (2025). https:\/\/doi.org\/10.1038\/s41598-025-01010-5","DOI":"10.1038\/s41598-025-01010-5"},{"issue":"13","key":"2360_CR27","doi-asserted-by":"publisher","first-page":"2049","DOI":"10.1177\/02783649241246557","volume":"43","author":"M Koptev","year":"2024","unstructured":"Koptev, M., Figueroa, N., Billard, A.: Reactive collision-free motion generation in joint space via dynamical systems and sampling-based mpc. Intl. J. Robot. Res. 43(13), 2049\u20132069 (2024). https:\/\/doi.org\/10.1177\/02783649241246557","journal-title":"Intl. J. Robot. Res."},{"key":"2360_CR28","doi-asserted-by":"crossref","unstructured":"Li, Y., Chi, X., Razmjoo, A., Calinon, S.: Configuration space distance fields for manipulation planning. In: Robotics: Science and systems (RSS) (2024). https:\/\/www.roboticsproceedings.org\/rss20\/p131.pdf","DOI":"10.15607\/RSS.2024.XX.131"},{"issue":"7","key":"2360_CR29","doi-asserted-by":"publisher","first-page":"3625","DOI":"10.3390\/s23073625","volume":"23","author":"J Orr","year":"2023","unstructured":"Orr, J., Dutta, A.: Multi-agent deep reinforcement learning for multi-robot applications: A survey. Sensors. 23(7), 3625 (2023). https:\/\/doi.org\/10.3390\/s23073625","journal-title":"Sensors."},{"key":"2360_CR30","doi-asserted-by":"publisher","unstructured":"Wang, X., Ding, S., Zhang, G.: Maddpg: A task offloading algorithm based on multi-agent deep reinforcement learning in vehicle-edge computing. In: Proceedings of the 2023 international conference on communication network and machine learning, pp. 408\u2013413 (2023). https:\/\/doi.org\/10.1145\/3640912.3640992","DOI":"10.1145\/3640912.3640992"},{"issue":"2","key":"2360_CR31","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.jai.2024.02.003","volume":"3","author":"Z Ning","year":"2024","unstructured":"Ning, Z., Xie, L.: A survey on multi-agent reinforcement learning and its application. J. Autom. Intell. 3(2), 73\u201391 (2024). https:\/\/doi.org\/10.1016\/j.jai.2024.02.003","journal-title":"J. Autom. Intell."},{"key":"2360_CR32","doi-asserted-by":"publisher","unstructured":"Lowe, R., Wu, Y.I., Tamar, A., Harb, J., Pieter\u00a0Abbeel, O., Mordatch, I.: Multi-agent actor-critic for mixed cooperative-competitive environments. Adv. Neural Inf. Process. Syst. 30 (2017). https:\/\/doi.org\/10.48550\/arXiv.1706.02275","DOI":"10.48550\/arXiv.1706.02275"},{"key":"2360_CR33","doi-asserted-by":"publisher","unstructured":"Bettini, M., Prorok, A., Moens, V.: Benchmarl: Benchmarking multi-agent reinforcement learning. J. Mach. Learn. Res. 25(217), 1\u201310 (2024). https:\/\/doi.org\/10.48550\/arXiv.2312.01472","DOI":"10.48550\/arXiv.2312.01472"},{"key":"2360_CR34","doi-asserted-by":"publisher","unstructured":"Vu, C.-T., Liu, Y.-C.: Deep reinforcement learning for multi-robot local path planning in dynamic environments. In: 2024 13th international workshop on robot motion and control (RoMoCo), pp. 267\u2013272 (2024). https:\/\/doi.org\/10.1109\/RoMoCo60539.2024.10604387. IEEE","DOI":"10.1109\/RoMoCo60539.2024.10604387"},{"key":"2360_CR35","doi-asserted-by":"crossref","unstructured":"Fuji, T., Ito, K., Matsumoto, K., Yano, K.: Deep multi-agent reinforcement learning using dnn-weight evolution to optimize supply chain performance. Proceedings of the 51st Hawaii international conference on system sciences. (2018). http:\/\/hdl.handle.net\/10125\/50044","DOI":"10.24251\/HICSS.2018.157"},{"key":"2360_CR36","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2024.3468770","author":"Z Zhang","year":"2024","unstructured":"Zhang, Z., Hong, J., Enayati, A.M.S., Najjaran, H.: Using implicit behavior cloning and dynamic movement primitive to facilitate reinforcement learning for robot motion planning. IEEE Trans. Rob. (2024). https:\/\/doi.org\/10.1109\/TRO.2024.3468770","journal-title":"IEEE Trans. Rob."},{"issue":"9","key":"2360_CR37","doi-asserted-by":"publisher","first-page":"14128","DOI":"10.1109\/TITS.2022.3144867","volume":"23","author":"L Le Mero","year":"2022","unstructured":"Le Mero, L., Yi, D., Dianati, M., Mouzakitis, A.: A survey on imitation learning techniques for end-to-end autonomous vehicles. IEEE Trans. Intell. Transp. Syst. 23(9), 14128\u201314147 (2022). https:\/\/doi.org\/10.1109\/TITS.2022.3144867","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"5","key":"2360_CR38","doi-asserted-by":"publisher","first-page":"6322","DOI":"10.1109\/TNNLS.2022.3213246","volume":"35","author":"B Zheng","year":"2022","unstructured":"Zheng, B., Verma, S., Zhou, J., Tsang, I.W., Chen, F.: Imitation learning: Progress, taxonomies and challenges. IEEE Trans. Neural Netw. Learn. Syst. 35(5), 6322\u20136337 (2022). https:\/\/doi.org\/10.1109\/TNNLS.2022.3213246","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"2360_CR39","doi-asserted-by":"publisher","unstructured":"Sun, S., Li, T., Chen, X., Dong, H., Wang, X.: Cooperative defense of autonomous surface vessels with quantity disadvantage using behavior cloning and deep reinforcement learning. Appl. Soft Comput. 164, 111968 (2024). https:\/\/doi.org\/10.1016\/j.asoc.2024.111968","DOI":"10.1016\/j.asoc.2024.111968"},{"key":"2360_CR40","doi-asserted-by":"publisher","unstructured":"Li, L., Zhang, X., Qian, C., Zhao, M., Wang, R.: Cross coordination of behavior clone and reinforcement learning for autonomous within-visual-range air combat. Neurocomputing. 584, 127591 (2024). https:\/\/doi.org\/10.1016\/j.neucom.2024.127591","DOI":"10.1016\/j.neucom.2024.127591"},{"key":"2360_CR41","doi-asserted-by":"publisher","unstructured":"Gavenski, N., Meneguzzi, F., Luck, M., Rodrigues, O.: A survey of imitation learning methods, environments and metrics. (2024). https:\/\/doi.org\/10.48550\/arXiv.2404.19456","DOI":"10.48550\/arXiv.2404.19456"},{"key":"2360_CR42","doi-asserted-by":"publisher","unstructured":"Foster, D.J., Block, A., Misra, D.: Is behavior cloning all you need? understanding horizon in imitation learning. In: NeurIPS (2024). https:\/\/doi.org\/10.48550\/arXiv.2407.15007","DOI":"10.48550\/arXiv.2407.15007"},{"key":"2360_CR43","doi-asserted-by":"publisher","unstructured":"Jiang, L., Pan, B., Dai, B., Sun, W., Jiang, N., Zhang, C.: Offline reinforcement learning with imbalanced datasets. (2023). https:\/\/doi.org\/10.48550\/arXiv.2307.02752","DOI":"10.48550\/arXiv.2307.02752"},{"key":"2360_CR44","doi-asserted-by":"publisher","unstructured":"Yu, X., coauthors: Wasserstein quality diversity imitation learning with limited demonstrations. In: AAMAS, pp. 2271\u20132273 (2025). https:\/\/doi.org\/10.5555\/3709347.3743867","DOI":"10.5555\/3709347.3743867"},{"key":"2360_CR45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3367329","author":"L Wang","year":"2024","unstructured":"Wang, L., Zhang, X., Su, H., Zhu, J.: A comprehensive survey of continual learning: Theory, method and application. IEEE Trans. Pattern Anal. Mach. Intell. (2024). https:\/\/doi.org\/10.1109\/TPAMI.2024.3367329","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2360_CR46","doi-asserted-by":"publisher","DOI":"10.7939\/r3-e65c-x854","author":"P Rahman","year":"2021","unstructured":"Rahman, P.: Toward generate-and-test algorithms for continual feature discovery. (2021). https:\/\/doi.org\/10.7939\/r3-e65c-x854","journal-title":"Toward generate-and-test algorithms for continual feature discovery."},{"key":"2360_CR47","unstructured":"Lyle, C., Zheng, Z., Nikishin, E., Pires, B.A., Pascanu, R., Dabney, W.: Understanding plasticity in neural networks. In: International conference on machine learning, pp. 23190\u201323211 (2023). https:\/\/proceedings.mlr.press\/v202\/lyle23b.html. PMLR"},{"key":"2360_CR48","doi-asserted-by":"publisher","unstructured":"Khetarpal, K., Riemer, M., Rish, I., Precup, D.: Towards continual reinforcement learning: A review and perspectives. J. Artif. Intell. Res. 75, 1401\u20131476 (2022). https:\/\/doi.org\/10.1613\/jair.1.13673","DOI":"10.1613\/jair.1.13673"},{"key":"2360_CR49","doi-asserted-by":"crossref","unstructured":"Abel, D., Barreto, A., Roy, B.V., Precup, D., Hasselt, H., Singh, S.: A definition of continual reinforcement learning. (2023) . arXiv preprint arXiv:2307.11046","DOI":"10.52202\/075280-2192"},{"key":"2360_CR50","doi-asserted-by":"publisher","unstructured":"Chen, R., Liu, X., Liu, T., Jiang, S., Xu, F., Yu, Y.: Foresight distribution adjustment for off-policy reinforcement learning. In: AAMAS 2024, Auckland, New Zealand (2024). https:\/\/doi.org\/10.5555\/3635637.3662880","DOI":"10.5555\/3635637.3662880"},{"key":"2360_CR51","doi-asserted-by":"publisher","unstructured":"Tang, H., Berseth, G.: Improving deep reinforcement learning by reducing the chain effect of value and policy churn. In: NeurIPS 2024 (2024). https:\/\/doi.org\/10.48550\/arXiv.2409.04792","DOI":"10.48550\/arXiv.2409.04792"},{"key":"2360_CR52","doi-asserted-by":"publisher","unstructured":"Kumar, S., Marklund, H., Van\u00a0Roy, B.: Maintaining plasticity in continual learning via regenerative regularization. (2023). arXiv preprint https:\/\/doi.org\/10.48550\/arXiv.2308.11958","DOI":"10.48550\/arXiv.2308.11958"},{"issue":"13","key":"2360_CR53","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick, J., Pascanu, R., Rabinowitz, N., Veness, J., Desjardins, G., Rusu, A.A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A., et al.: Overcoming catastrophic forgetting in neural networks. Proc. Natl. Acad. Sci. 114(13), 3521\u20133526 (2017). https:\/\/doi.org\/10.1073\/pnas.1611835114","journal-title":"Proc. Natl. Acad. Sci."},{"key":"2360_CR54","doi-asserted-by":"publisher","unstructured":"Huang, Z., Liang, M., Liang, S., He, W.: Altersgd: Finding flat minima for continual learning by alternative training. (2021). arXiv preprint https:\/\/doi.org\/10.48550\/arXiv.2107.05804","DOI":"10.48550\/arXiv.2107.05804"},{"issue":"8026","key":"2360_CR55","doi-asserted-by":"publisher","first-page":"768","DOI":"10.1038\/s41586-024-07711-7","volume":"632","author":"S Dohare","year":"2024","unstructured":"Dohare, S., Hernandez-Garcia, J.F., Lan, Q., Rahman, P., White, A., Sutton, R.S., Fyshe, A., White, M., Mahmood, A.R.: Loss of plasticity in deep continual learning. Nat. 632(8026), 768\u2013774 (2024). https:\/\/doi.org\/10.1038\/s41586-024-07711-7","journal-title":"Nat."},{"key":"2360_CR56","unstructured":"Sun, M., Liu, Z., Bair, A., Kolter, J.Z.: A simple and effective pruning approach for large language models. (2023). arXiv preprint arXiv:2306.11695"},{"key":"2360_CR57","doi-asserted-by":"publisher","unstructured":"Zhu, Y., Wong, J., Mandlekar, A., Mart\u00edn-Mart\u00edn, R., Joshi, A., Nasiriany, S., Zhu, Y.: robosuite: A modular simulation framework and benchmark for robot learning. (2020). arXiv preprint https:\/\/doi.org\/10.48550\/arXiv.2009.12293","DOI":"10.48550\/arXiv.2009.12293"},{"key":"2360_CR58","unstructured":"Nikishin, E., Schwarzer, M., D\u2019Oro, P., Bacon, P.-L., Courville, A.: The primacy bias in deep reinforcement learning. In: International conference on machine learning, pp. 16828\u201316847 (2022). https:\/\/proceedings.mlr.press\/v162\/nikishin22a. PMLR"},{"key":"2360_CR59","doi-asserted-by":"publisher","unstructured":"Haarnoja, T., Pong, V., Zhou, A., Dalal, M., Abbeel, P., Levine, S.: Composable deep reinforcement learning for robotic manipulation. In: 2018 IEEE international conference on robotics and automation (ICRA), pp. 6244\u20136251 (2018). https:\/\/doi.org\/10.1109\/ICRA.2018.8460756. IEEE","DOI":"10.1109\/ICRA.2018.8460756"},{"key":"2360_CR60","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: International conference on machine learning, pp. 1861\u20131870 (2018). https:\/\/proceedings.mlr.press\/v80\/haarnoja18b. PMLR"},{"key":"2360_CR61","unstructured":"Sharifani, K., Amini, M.: Machine learning and deep learning: A review of methods and applications. World Inf. Technol. Eng. J. 10(07), 3897\u20133904 (2023). https:\/\/ssrn.com\/abstract=4458723"},{"issue":"1","key":"2360_CR62","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1023\/A:1018064306595","volume":"22","author":"S Mahadevan","year":"1996","unstructured":"Mahadevan, S.: Average reward reinforcement learning: Foundations, algorithms, and empirical results. Mach. Learn. 22(1), 159\u2013195 (1996). https:\/\/doi.org\/10.1023\/A:1018064306595","journal-title":"Mach. Learn."}],"container-title":["Journal of Intelligent & Robotic Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10846-026-02360-6","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-026-02360-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10846-026-02360-6.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T07:39:31Z","timestamp":1774856371000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10846-026-02360-6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,31]]},"references-count":62,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["2360"],"URL":"https:\/\/doi.org\/10.1007\/s10846-026-02360-6","relation":{},"ISSN":["1573-0409"],"issn-type":[{"value":"1573-0409","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,31]]},"assertion":[{"value":"24 October 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 January 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 January 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"21"}}