[{"conference":{"location":"Barcelona","name":"9th Iberian Robotics Conference (ROBOT) ","end_date":"2026-11-20","start_date":"2026-11-18"},"keyword":["Reinforcement Learning","Robotic Manipulation","Morphology Generalization","Sim-to-Real Transfer"],"quality_controlled":"1","project":[{"name":"Institute for Building Intelligence","_id":"A827C0AA-C7DA-11E9-B0AE-1F4CB252D58D"}],"title":"Adapting to Variable Kinematic Configurations: A Causal-Kinematic Attention Approach for Robotic Control","year":"2026","type":"conference","_id":"7175","citation":{"apa":"Mayer, P. T., &#38; Rexilius, J. (n.d.). Adapting to Variable Kinematic Configurations: A Causal-Kinematic Attention Approach for Robotic Control. Presented at the 9th Iberian Robotics Conference (ROBOT) , Barcelona.","chicago":"Mayer, Patrick Thomas, and Jan Rexilius. “Adapting to Variable Kinematic Configurations: A Causal-Kinematic Attention Approach for Robotic Control,” n.d.","alphadin":"<span style=\"font-variant:small-caps;\">Mayer, Patrick Thomas</span> ; <span style=\"font-variant:small-caps;\">Rexilius, Jan</span>: Adapting to Variable Kinematic Configurations: A Causal-Kinematic Attention Approach for Robotic Control. In:","mla":"Mayer, Patrick Thomas, and Jan Rexilius. <i>Adapting to Variable Kinematic Configurations: A Causal-Kinematic Attention Approach for Robotic Control</i>.","ieee":"P. T. Mayer and J. Rexilius, “Adapting to Variable Kinematic Configurations: A Causal-Kinematic Attention Approach for Robotic Control,” presented at the 9th Iberian Robotics Conference (ROBOT) , Barcelona.","short":"P.T. Mayer, J. Rexilius, in: n.d.","bibtex":"@inproceedings{Mayer_Rexilius, title={Adapting to Variable Kinematic Configurations: A Causal-Kinematic Attention Approach for Robotic Control}, author={Mayer, Patrick Thomas and Rexilius, Jan} }","ama":"Mayer PT, Rexilius J. Adapting to Variable Kinematic Configurations: A Causal-Kinematic Attention Approach for Robotic Control."},"author":[{"id":"244831","last_name":"Mayer","orcid":"0009-0009-6800-1273","first_name":"Patrick Thomas","full_name":"Mayer, Patrick Thomas","orcid_put_code_url":"https://api.orcid.org/v2.0/0009-0009-6800-1273/work/227375532"},{"orcid_put_code_url":"https://api.orcid.org/v2.0/0000-0002-4579-214X/work/227375533","full_name":"Rexilius, Jan","first_name":"Jan","last_name":"Rexilius","orcid":"0000-0002-4579-214X","id":"245736"}],"department":[{"_id":"102"}],"date_created":"2026-09-21T16:34:09Z","publication_status":"accepted","status":"public","date_updated":"2026-09-21T19:31:42Z","abstract":[{"text":"Deep reinforcement learning (RL) policies for robotic control typically overfit to a single hardware configuration. Any change to the kinematic chain breaks the learned mapping and requires complete retraining. This paper investigates whether combining self-attention mechanisms with explicit spatial observations can improve a policy’s adaptability to varying kinematic topologies. We train a single RL agent to control a robotic manipulator across different degrees of freedom (DOF), ranging from a restricted 4-DOF mode to a fully redundant 7-DOF configuration. Instead of fixed-length state vectors, the method processes the active joints as a variable-length sequence in an attention buffer, enriching each joint’s representation with its relative spatial routing and geometric Jacobian influence. This structure allows the agent to dynamically evaluate the physical utility of its available actuators. The proposed Architecture reaches a success rate of 82.1% across trained topologies and 66.6% on unseen configurations, outperforming MLP and generic attention baselines while remaining nearly collisionfree. Finally, we demonstrate successful sim-to-real transfer by deploying the simulation-trained agent on a physical Franka Emika Panda manipulator.","lang":"eng"}],"language":[{"iso":"eng"}],"user_id":"244831"},{"date_updated":"2026-09-21T19:31:37Z","status":"public","publication_status":"accepted","date_created":"2026-09-21T16:30:06Z","user_id":"244831","abstract":[{"lang":"eng","text":"This paper presents a hybrid control architecture for dynamic robotic picking tasks. The framework combines a Deep Reinforcement Learning policy for high-level interception with a dedicated Inverse Kinematics controller for precise terminal grasping, while mitigating precision limitations of monolithic learning-based approaches. The framework utilizes a Proximal Policy Optimization agent to approach moving targets, seamlessly transitioning to an Inverse Kinematics solver that reduces terminal orientational and positional errors while minimizing cumulative control effort. To facilitate deployment on physical hardware, a robust sim-to-real pipeline incorporating system identification, domain randomization, and latency injection is employed. Experimental results on a physical Franka Emika Panda manipulator validate this hybrid architecture. The system achieves an 80% success rate in pick-and-place tasks, compared to 60.8% for unadapted baselines, with no safety-critical violations such as joint limit breaches or collisions observed during testing."}],"language":[{"iso":"eng"}],"_id":"7174","citation":{"ama":"Mayer PT, Rexilius J. A Hybrid Control Framework Using Reinforcement Learning for Dynamic Robotic Manipulation and Sim-to-Real Transfer.","bibtex":"@inproceedings{Mayer_Rexilius, title={A Hybrid Control Framework Using Reinforcement Learning for Dynamic Robotic Manipulation and Sim-to-Real Transfer}, author={Mayer, Patrick Thomas and Rexilius, Jan} }","short":"P.T. Mayer, J. Rexilius, in: n.d.","mla":"Mayer, Patrick Thomas, and Jan Rexilius. <i>A Hybrid Control Framework Using Reinforcement Learning for Dynamic Robotic Manipulation and Sim-to-Real Transfer</i>.","ieee":"P. T. Mayer and J. Rexilius, “A Hybrid Control Framework Using Reinforcement Learning for Dynamic Robotic Manipulation and Sim-to-Real Transfer,” presented at the 26th International Conference on Control, Automation and Systems (ICCAS), Sapporo.","alphadin":"<span style=\"font-variant:small-caps;\">Mayer, Patrick Thomas</span> ; <span style=\"font-variant:small-caps;\">Rexilius, Jan</span>: A Hybrid Control Framework Using Reinforcement Learning for Dynamic Robotic Manipulation and Sim-to-Real Transfer. In:","apa":"Mayer, P. T., &#38; Rexilius, J. (n.d.). A Hybrid Control Framework Using Reinforcement Learning for Dynamic Robotic Manipulation and Sim-to-Real Transfer. Presented at the 26th International Conference on Control, Automation and Systems (ICCAS), Sapporo.","chicago":"Mayer, Patrick Thomas, and Jan Rexilius. “A Hybrid Control Framework Using Reinforcement Learning for Dynamic Robotic Manipulation and Sim-to-Real Transfer,” n.d."},"department":[{"_id":"102"}],"author":[{"full_name":"Mayer, Patrick Thomas","orcid_put_code_url":"https://api.orcid.org/v2.0/0009-0009-6800-1273/work/227375528","orcid":"0009-0009-6800-1273","last_name":"Mayer","first_name":"Patrick Thomas","id":"244831"},{"first_name":"Jan","last_name":"Rexilius","orcid":"0000-0002-4579-214X","orcid_put_code_url":"https://api.orcid.org/v2.0/0000-0002-4579-214X/work/227375529","full_name":"Rexilius, Jan","id":"245736"}],"year":"2026","type":"conference","conference":{"name":"26th International Conference on Control, Automation and Systems (ICCAS)","location":"Sapporo","end_date":"2026-10-30","start_date":"2026-10-27"},"title":"A Hybrid Control Framework Using Reinforcement Learning for Dynamic Robotic Manipulation and Sim-to-Real Transfer","project":[{"name":"Institute for Building Intelligence","_id":"A827C0AA-C7DA-11E9-B0AE-1F4CB252D58D"}],"quality_controlled":"1","keyword":["Reinforcement Learning","Hybrid Control","Sim-to-Real","Robotic Manipulation","Inverse Kinematics."]},{"type":"conference","year":"2026","project":[{"name":"Institute for Building Intelligence","_id":"A827C0AA-C7DA-11E9-B0AE-1F4CB252D58D"}],"quality_controlled":"1","title":"Reinforcement Learning-based MAV Navigation With Parameterized Waypoints: Incorporating Orientation, Speed Limits, and Corridor Constraints","keyword":["MAV navigation","Reinforcement learning","Constrained navigation","Control barrier functions"],"conference":{"start_date":"2026-11-18","location":"Barcelona","name":"9th Iberian Robotics Conference (ROBOT)","end_date":"2026-11-20"},"abstract":[{"text":"Reinforcement learning has achieved state-of-the-art performance in MAV control, waypoint flight, and obstacle avoidance. However, existing RL approaches often assume fixed objectives and constraints, with flight behavior largely limited by vehicle dynamics and orientation considered only when required for locomotion. Classical planning and model predictive control handle such constraints explicitly, but require optimization or replanning. This motivates methods that combine learned local control with explicit constraint handling. We combine reinforcement learning with control barrier functions to improve constraint-aware execution. We propose parameterized waypoints that encode orientation, velocity, and corridor constraints. Simulation and real-world experiments show that a single policy can execute different constraint-parameterized navigation scenarios, revealing scenario-dependent trade-offs between traversal time, tracking accuracy, and constraint satisfaction.","lang":"eng"}],"language":[{"iso":"eng"}],"user_id":"229807","publication_status":"accepted","date_created":"2026-09-21T14:31:38Z","date_updated":"2026-09-21T14:33:10Z","status":"public","author":[{"first_name":"André","last_name":"Kirsch","full_name":"Kirsch, André","id":"229807"},{"last_name":"Rexilius","orcid":"0000-0002-4579-214X","first_name":"Jan","full_name":"Rexilius, Jan","orcid_put_code_url":"https://api.orcid.org/v2.0/0000-0002-4579-214X/work/227345663","id":"245736"}],"citation":{"apa":"Kirsch, A., &#38; Rexilius, J. (n.d.). Reinforcement Learning-based MAV Navigation With Parameterized Waypoints: Incorporating Orientation, Speed Limits, and Corridor Constraints. Presented at the 9th Iberian Robotics Conference (ROBOT), Barcelona.","chicago":"Kirsch, André, and Jan Rexilius. “Reinforcement Learning-Based MAV Navigation With Parameterized Waypoints: Incorporating Orientation, Speed Limits, and Corridor Constraints,” n.d.","ama":"Kirsch A, Rexilius J. Reinforcement Learning-based MAV Navigation With Parameterized Waypoints: Incorporating Orientation, Speed Limits, and Corridor Constraints.","bibtex":"@inproceedings{Kirsch_Rexilius, title={Reinforcement Learning-based MAV Navigation With Parameterized Waypoints: Incorporating Orientation, Speed Limits, and Corridor Constraints}, author={Kirsch, André and Rexilius, Jan} }","short":"A. Kirsch, J. Rexilius, in: n.d.","ieee":"A. Kirsch and J. Rexilius, “Reinforcement Learning-based MAV Navigation With Parameterized Waypoints: Incorporating Orientation, Speed Limits, and Corridor Constraints,” presented at the 9th Iberian Robotics Conference (ROBOT), Barcelona.","mla":"Kirsch, André, and Jan Rexilius. <i>Reinforcement Learning-Based MAV Navigation With Parameterized Waypoints: Incorporating Orientation, Speed Limits, and Corridor Constraints</i>.","alphadin":"<span style=\"font-variant:small-caps;\">Kirsch, André</span> ; <span style=\"font-variant:small-caps;\">Rexilius, Jan</span>: Reinforcement Learning-based MAV Navigation With Parameterized Waypoints: Incorporating Orientation, Speed Limits, and Corridor Constraints. In:"},"_id":"7173"},{"file":[{"date_created":"2024-03-14T11:32:13Z","access_level":"open_access","creator":"fgrumbach1","date_updated":"2024-03-14T11:32:13Z","success":1,"content_type":"application/pdf","relation":"main_file","file_name":"Diss_FGrumbach_2024_Final.pdf","file_size":7859995,"file_id":"4393"}],"place":"Bernburg","year":"2024","supervisor":[{"first_name":"Sebastian","last_name":"Trojahn","full_name":"Trojahn, Sebastian"}],"tmp":{"image":"/images/cc_by.png","short":"CC BY (4.0)","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode"},"publisher":"Universitäts- und Landesbibliothek Sachsen-Anhalt","type":"dissertation","doi":"10.25673/115290","alternative_id":["5468"],"has_accepted_license":"1","keyword":["Produktionsplanung und -steuerung","Operations Research","Machine Learning","Reinforcement Learning"],"title":"Feldsynchrone Ablaufplanung dynamischer Fertigungsprozesse mit Techniken des maschinellen Lernens [kumulative Dissertation]","urn":"urn:nbn:de:hbz:bi10-43927","oa":"1","file_date_updated":"2024-03-14T11:32:13Z","date_created":"2024-03-14T11:32:15Z","publication_status":"published","status":"public","date_updated":"2026-07-06T12:23:58Z","publication_identifier":{"eisbn":["978-3-96057-174-2"]},"language":[{"iso":"ger"}],"user_id":"33976","_id":"4392","citation":{"apa":"Grumbach, F. (2024). <i>Feldsynchrone Ablaufplanung dynamischer Fertigungsprozesse mit Techniken des maschinellen Lernens [kumulative Dissertation]</i>. Bernburg: Universitäts- und Landesbibliothek Sachsen-Anhalt. <a href=\"https://doi.org/10.25673/115290\">https://doi.org/10.25673/115290</a>","chicago":"Grumbach, Felix. <i>Feldsynchrone Ablaufplanung dynamischer Fertigungsprozesse mit Techniken des maschinellen Lernens [kumulative Dissertation]</i>. Bernburg: Universitäts- und Landesbibliothek Sachsen-Anhalt, 2024. <a href=\"https://doi.org/10.25673/115290\">https://doi.org/10.25673/115290</a>.","bibtex":"@book{Grumbach_2024, place={Bernburg}, title={Feldsynchrone Ablaufplanung dynamischer Fertigungsprozesse mit Techniken des maschinellen Lernens [kumulative Dissertation]}, DOI={<a href=\"https://doi.org/10.25673/115290\">10.25673/115290</a>}, publisher={Universitäts- und Landesbibliothek Sachsen-Anhalt}, author={Grumbach, Felix}, year={2024} }","ama":"Grumbach F. <i>Feldsynchrone Ablaufplanung dynamischer Fertigungsprozesse mit Techniken des maschinellen Lernens [kumulative Dissertation]</i>. Bernburg: Universitäts- und Landesbibliothek Sachsen-Anhalt; 2024. doi:<a href=\"https://doi.org/10.25673/115290\">10.25673/115290</a>","alphadin":"<span style=\"font-variant:small-caps;\">Grumbach, Felix</span>: <i>Feldsynchrone Ablaufplanung dynamischer Fertigungsprozesse mit Techniken des maschinellen Lernens [kumulative Dissertation]</i>. Bernburg : Universitäts- und Landesbibliothek Sachsen-Anhalt, 2024","ieee":"F. Grumbach, <i>Feldsynchrone Ablaufplanung dynamischer Fertigungsprozesse mit Techniken des maschinellen Lernens [kumulative Dissertation]</i>. Bernburg: Universitäts- und Landesbibliothek Sachsen-Anhalt, 2024.","mla":"Grumbach, Felix. <i>Feldsynchrone Ablaufplanung dynamischer Fertigungsprozesse mit Techniken des maschinellen Lernens [kumulative Dissertation]</i>. Universitäts- und Landesbibliothek Sachsen-Anhalt, 2024, doi:<a href=\"https://doi.org/10.25673/115290\">10.25673/115290</a>.","short":"F. Grumbach, Feldsynchrone Ablaufplanung dynamischer Fertigungsprozesse mit Techniken des maschinellen Lernens [kumulative Dissertation], Universitäts- und Landesbibliothek Sachsen-Anhalt, Bernburg, 2024."},"main_file_link":[{"url":"http://dx.doi.org/10.25673/115290","open_access":"1"}],"author":[{"id":"243801","orcid_put_code_url":"https://api.orcid.org/v2.0/0000-0001-6348-7897/work/156390666","full_name":"Grumbach, Felix","first_name":"Felix","last_name":"Grumbach","orcid":"0000-0001-6348-7897"}]},{"date_updated":"2026-05-19T14:08:33Z","publication_identifier":{"eissn":["2073-4360"]},"author":[{"first_name":"Niklas","last_name":"Panneke","full_name":"Panneke, Niklas"},{"id":"223776","orcid":"0000-0003-0695-3905","last_name":"Ehrmann","first_name":"Andrea","full_name":"Ehrmann, Andrea","orcid_put_code_url":"https://api.orcid.org/v2.0/0000-0003-0695-3905/work/181737412"}],"file":[{"date_created":"2023-03-15T15:58:24Z","access_level":"open_access","date_updated":"2023-03-15T15:58:24Z","creator":"aehrmann","success":1,"content_type":"application/pdf","relation":"main_file","file_name":"_2023_Panneke_Polymers15_983.pdf","file_size":7726320,"file_id":"2603"}],"tmp":{"image":"/images/cc_by.png","short":"CC BY (4.0)","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode"},"doi":"10.3390/polym15040983","type":"journal_article","volume":15,"urn":"urn:nbn:de:hbz:bi10-26025","date_created":"2023-03-15T15:59:16Z","publication_status":"published","status":"public","publication":"Polymers","language":[{"iso":"eng"}],"user_id":"250307","_id":"2602","intvolume":"        15","citation":{"ieee":"N. Panneke and A. Ehrmann, “Stab-Resistant Polymers—Recent Developments in Materials and Structures,” <i>Polymers</i>, vol. 15, no. 4, 2023.","mla":"Panneke, Niklas, and Andrea Ehrmann. “Stab-Resistant Polymers—Recent Developments in Materials and Structures.” <i>Polymers</i>, vol. 15, no. 4, 983, MDPI AG, 2023, doi:<a href=\"https://doi.org/10.3390/polym15040983\">10.3390/polym15040983</a>.","alphadin":"<span style=\"font-variant:small-caps;\">Panneke, Niklas</span> ; <span style=\"font-variant:small-caps;\">Ehrmann, Andrea</span>: Stab-Resistant Polymers—Recent Developments in Materials and Structures. In: <i>Polymers</i> Bd. 15, MDPI AG (2023), Nr. 4","short":"N. Panneke, A. Ehrmann, Polymers 15 (2023).","ama":"Panneke N, Ehrmann A. Stab-Resistant Polymers—Recent Developments in Materials and Structures. <i>Polymers</i>. 2023;15(4). doi:<a href=\"https://doi.org/10.3390/polym15040983\">10.3390/polym15040983</a>","bibtex":"@article{Panneke_Ehrmann_2023, title={Stab-Resistant Polymers—Recent Developments in Materials and Structures}, volume={15}, DOI={<a href=\"https://doi.org/10.3390/polym15040983\">10.3390/polym15040983</a>}, number={4983}, journal={Polymers}, publisher={MDPI AG}, author={Panneke, Niklas and Ehrmann, Andrea}, year={2023} }","apa":"Panneke, N., &#38; Ehrmann, A. (2023). Stab-Resistant Polymers—Recent Developments in Materials and Structures. <i>Polymers</i>, <i>15</i>(4). <a href=\"https://doi.org/10.3390/polym15040983\">https://doi.org/10.3390/polym15040983</a>","chicago":"Panneke, Niklas, and Andrea Ehrmann. “Stab-Resistant Polymers—Recent Developments in Materials and Structures.” <i>Polymers</i> 15, no. 4 (2023). <a href=\"https://doi.org/10.3390/polym15040983\">https://doi.org/10.3390/polym15040983</a>."},"main_file_link":[{"open_access":"1"}],"article_type":"review","article_number":"983","year":"2023","publisher":"MDPI AG","has_accepted_license":"1","issue":"4","funded_apc":"1","keyword":["body armor","additive manufacturing","functional textiles","sensory textiles","shear-thickening fluid","reinforcement","stab protection","VPAM-KDIW","HOSDB"],"title":"Stab-Resistant Polymers—Recent Developments in Materials and Structures","quality_controlled":"1","oa":"1","file_date_updated":"2023-03-15T15:58:24Z"},{"language":[{"iso":"eng"}],"publication_identifier":{"issn":["0956-5515"],"eissn":["1572-8145"]},"user_id":"245729","publication_status":"published","date_created":"2023-01-10T13:08:37Z","publication":"Journal of Intelligent Manufacturing","date_updated":"2026-06-25T11:42:46Z","status":"public","author":[{"last_name":"Grumbach","orcid":"0000-0001-6348-7897","first_name":"Felix","full_name":"Grumbach, Felix","orcid_put_code_url":"https://api.orcid.org/v2.0/0000-0001-6348-7897/work/218753400","id":"243801"},{"full_name":"Müller, Anna","last_name":"Müller","first_name":"Anna"},{"last_name":"Reusch","first_name":"Pascal","full_name":"Reusch, Pascal"},{"first_name":"Sebastian","last_name":"Trojahn","full_name":"Trojahn, Sebastian"}],"_id":"2295","citation":{"chicago":"Grumbach, Felix, Anna Müller, Pascal Reusch, and Sebastian Trojahn. “Robust-Stable Scheduling in Dynamic Flow Shops Based on Deep Reinforcement Learning.” <i>Journal of Intelligent Manufacturing</i>, 2022. <a href=\"https://doi.org/10.1007/s10845-022-02069-x\">https://doi.org/10.1007/s10845-022-02069-x</a>.","apa":"Grumbach, F., Müller, A., Reusch, P., &#38; Trojahn, S. (2022). Robust-stable scheduling in dynamic flow shops based on deep reinforcement learning. <i>Journal of Intelligent Manufacturing</i>. <a href=\"https://doi.org/10.1007/s10845-022-02069-x\">https://doi.org/10.1007/s10845-022-02069-x</a>","alphadin":"<span style=\"font-variant:small-caps;\">Grumbach, Felix</span> ; <span style=\"font-variant:small-caps;\">Müller, Anna</span> ; <span style=\"font-variant:small-caps;\">Reusch, Pascal</span> ; <span style=\"font-variant:small-caps;\">Trojahn, Sebastian</span>: Robust-stable scheduling in dynamic flow shops based on deep reinforcement learning. In: <i>Journal of Intelligent Manufacturing</i>, Springer Science and Business Media LLC (2022)","ieee":"F. Grumbach, A. Müller, P. Reusch, and S. Trojahn, “Robust-stable scheduling in dynamic flow shops based on deep reinforcement learning,” <i>Journal of Intelligent Manufacturing</i>, 2022.","mla":"Grumbach, Felix, et al. “Robust-Stable Scheduling in Dynamic Flow Shops Based on Deep Reinforcement Learning.” <i>Journal of Intelligent Manufacturing</i>, Springer Science and Business Media LLC, 2022, doi:<a href=\"https://doi.org/10.1007/s10845-022-02069-x\">10.1007/s10845-022-02069-x</a>.","short":"F. Grumbach, A. Müller, P. Reusch, S. Trojahn, Journal of Intelligent Manufacturing (2022).","bibtex":"@article{Grumbach_Müller_Reusch_Trojahn_2022, title={Robust-stable scheduling in dynamic flow shops based on deep reinforcement learning}, DOI={<a href=\"https://doi.org/10.1007/s10845-022-02069-x\">10.1007/s10845-022-02069-x</a>}, journal={Journal of Intelligent Manufacturing}, publisher={Springer Science and Business Media LLC}, author={Grumbach, Felix and Müller, Anna and Reusch, Pascal and Trojahn, Sebastian}, year={2022} }","ama":"Grumbach F, Müller A, Reusch P, Trojahn S. Robust-stable scheduling in dynamic flow shops based on deep reinforcement learning. <i>Journal of Intelligent Manufacturing</i>. 2022. doi:<a href=\"https://doi.org/10.1007/s10845-022-02069-x\">10.1007/s10845-022-02069-x</a>"},"main_file_link":[{"open_access":"1","url":"https://link.springer.com/article/10.1007/s10845-022-02069-x"}],"publisher":"Springer Science and Business Media LLC","tmp":{"image":"/images/cc_by.png","short":"CC BY (4.0)","name":"Creative Commons Attribution 4.0 International Public License (CC-BY 4.0)","legal_code_url":"https://creativecommons.org/licenses/by/4.0/legalcode"},"doi":"10.1007/s10845-022-02069-x","type":"journal_article","year":"2022","jel":["C6"],"article_type":"original","title":"Robust-stable scheduling in dynamic flow shops based on deep reinforcement learning","quality_controlled":"1","keyword":["Dynamic flow shop","Predictive scheduling","Proactive scheduling","Robust scheduling","Reinforcement learning","Simheuristics"],"oa":"1"}]