@inproceedings{RitzRatkePhanetal.2021, author = {Ritz, Fabian and Ratke, Daniel and Phan, Thomy and Belzner, Lenz and Linnhoff-Popien, Claudia}, title = {A sustainable ecosystem through emergent cooperation in multi-agent reinforcement learning}, volume = {2021}, pages = {isal_a_00399}, booktitle = {Proceedings of the Artificial Life Conference 2021}, publisher = {MIT Press}, address = {Cambridge}, doi = {https://doi.org/10.1162/isal_a_00399}, year = {2021}, language = {en} } @inproceedings{SchmidMuellerBelzneretal.2021, author = {Schmid, Kyrill and M{\"u}ller, Robert and Belzner, Lenz and Tochtermann, Johannes and Linnhoff-Popien, Claudia}, title = {Distributed emergent agreements with deep reinforcement learning}, booktitle = {2021 International Joint Conference on Neural Networks (IJCNN) Proceedings}, publisher = {IEEE}, address = {Piscataway}, isbn = {978-1-6654-3900-8}, issn = {2161-4407}, doi = {https://doi.org/10.1109/IJCNN52387.2021.9533333}, year = {2021}, language = {en} } @inproceedings{PierothFitchBelzner2022, author = {Pieroth, Fabian Raoul and Fitch, Katherine and Belzner, Lenz}, title = {Detecting Influence Structures in Multi-Agent Reinforcement Learning Systems}, url = {http://aaai-rlg.mlanctot.info/sched.html\#poster1}, year = {2022}, language = {en} } @inproceedings{UnoldWintergerstBelzneretal.2021, author = {Unold, Florian von and Wintergerst, Monika and Belzner, Lenz and Groh, Georg}, title = {DYME: a dynamic metric for dialog modeling learned from human conversations}, booktitle = {Neural Information Processing: 28th International Conference, ICONIP 2021, Sanur, Bali, Indonesia, December 8-12, 2021, Proceedings, Part V}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-92307-5}, doi = {https://doi.org/10.1007/978-3-030-92307-5_30}, pages = {257 -- 264}, year = {2021}, language = {en} } @inproceedings{PhanRitzBelzneretal.2021, author = {Phan, Thomy and Ritz, Fabian and Belzner, Lenz and Altmann, Philipp and Gabor, Thomas and Linnhoff-Popien, Claudia}, title = {VAST: Value Function Factorization with Variable Agent Sub-Teams}, booktitle = {Advances in Neural Information Processing Systems 34 (NeurIPS 2021)}, publisher = {Neural Information Processing Systems Foundation, Inc. (NIPS)}, url = {https://proceedings.neurips.cc/paper/2021/hash/c97e7a5153badb6576d8939469f58336-Abstract.html}, year = {2021}, language = {en} } @inproceedings{SchmidBelznerLinnhoffPopien2021, author = {Schmid, Kyrill and Belzner, Lenz and Linnhoff-Popien, Claudia}, title = {Learning to penalize other learning agents}, volume = {2021}, pages = {isal_a_00369}, booktitle = {Proceedings of the Artificial Life Conference 2021}, publisher = {MIT Press}, address = {Cambridge}, doi = {https://doi.org/10.1162/isal_a_00369}, year = {2021}, language = {en} } @inproceedings{KarpenahalliRamakrishnaMohanZeinalyetal.2025, author = {Karpenahalli Ramakrishna, Chidvilas and Mohan, Adithya and Zeinaly, Zahra and Belzner, Lenz}, title = {The Evolution of Criticality in Deep Reinforcement Learning}, booktitle = {Proceedings of the 17th International Conference on Agents and Artificial Intelligence (ICAART 2025) - Volume 3}, editor = {Rocha, Ana Paula and Steels, Luc and van den Herik, Jaap}, publisher = {SciTePress}, address = {Set{\´u}bal}, isbn = {978-989-758-737-5}, doi = {https://doi.org/10.5220/0013114200003890}, pages = {217 -- 224}, year = {2025}, abstract = {In Reinforcement Learning (RL), certain states demand special attention due to their significant influence on outcomes; these are identified as critical states. The concept of criticality is essential for the development of effective and robust policies and to improve overall trust in RL agents in real-world applications like autonomous driving. The current paper takes a deep dive into criticality and studies the evolution of criticality throughout training. The experiments are conducted on a new, simple yet intuitive continuous cliff maze environment and the Highway-env autonomous driving environment. Here, a novel finding is reported that criticality is not only learnt by the agent but can also be unlearned. We hypothesize that diversity in experiences is necessary for effective criticality quantification which is majorly driven by the chosen exploration strategy. This close relationship between exploration and criticality is studied utilizing two different strategies namely the ex ponential ε-decay and the adaptive ε-decay. The study supports the idea that effective exploration plays a crucial role in accurately identifying and understanding critical states.}, language = {en} } @inproceedings{PhanSommerAltmannetal.2022, author = {Phan, Thomy and Sommer, Felix and Altmann, Philipp and Ritz, Fabian and Belzner, Lenz and Linnhoff-Popien, Claudia}, title = {Emergent Cooperation from Mutual Acknowledgment Exchange}, booktitle = {AAMAS '22: Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems}, publisher = {International Foundation for Autonomous Agents and Multiagent Systems}, address = {Richland}, isbn = {978-1-4503-9213-6}, doi = {https://dl.acm.org/doi/10.5555/3535850.3535967}, pages = {1047 -- 1055}, year = {2022}, language = {en} } @inproceedings{StenzelSchmidKoelleetal.2024, author = {Stenzel, Gerhard and Schmid, Kyrill and K{\"o}lle, Michael and Altmann, Philipp and Lingsch-Rosenfeld, Marian and Zorn, Maximilian and B{\"u}cher, Tim and Gabor, Thomas and Wirsing, Martin and Belzner, Lenz}, title = {SEGym: Optimizing Large Language Model Assisted Software Engineering Agents with Reinforcement Learning}, booktitle = {Bridging the Gap Between AI and Reality, Second International Conference, AISoLA 2024, Crete, Greece, October 30 - November 3, 2024, Proceedings}, editor = {Steffen, Bernhard}, publisher = {Springer}, address = {Cham}, isbn = {978-3-031-75434-0}, doi = {https://doi.org/10.1007/978-3-031-75434-0_8}, pages = {107 -- 124}, year = {2024}, language = {en} } @article{PosorBelznerKnapp2019, author = {Posor, Jorrit Enzio and Belzner, Lenz and Knapp, Alexander}, title = {Joint Action Learning for Multi-Agent Cooperation using Recurrent Reinforcement Learning}, volume = {4}, journal = {Digitale Welt}, number = {1}, publisher = {Digitale Welt Academy}, address = {M{\"u}nchen}, issn = {2569-1996}, doi = {https://doi.org/10.1007/s42354-019-0239-y}, pages = {79 -- 84}, year = {2019}, language = {en} }