@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{BelznerSchmidPhanetal.2018, author = {Belzner, Lenz and Schmid, Kyrill and Phan, Thomy and Gabor, Thomas and Wirsing, Martin}, title = {The sharer's dilemma in collective adaptive systems of self-interested agents}, booktitle = {Leveraging Applications of Formal Methods, Verification and Validation : Distributed Systems : 8th International Symposium, ISoLA 2018; Limassol, Cyprus, November 5-9, 2018; Proceedings, Part III}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-03423-8}, doi = {https://doi.org/10.1007/978-3-030-03424-5_16}, pages = {241 -- 256}, year = {2018}, language = {en} } @inproceedings{SchmidBelznerPhanetal.2020, author = {Schmid, Kyrill and Belzner, Lenz and Phan, Thomy and Gabor, Thomas and Linnhoff-Popien, Claudia}, title = {Multi-agent reinforcement learning for bargaining under risk and asymmetric information}, booktitle = {Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART 2020}, editor = {Rocha, Ana and Steels, Luc and Herik, Jaap van den}, publisher = {SciTePress}, address = {Set{\´u}bal}, isbn = {978-989-758-395-7}, issn = {2184-433X}, doi = {https://doi.org/10.5220/0008913901440151}, pages = {144 -- 151}, year = {2020}, abstract = {In cooperative game theory bargaining games refer to situations where players can agree to any one of a variety of outcomes but there is a conflict on which specific outcome to choose. However, the players cannot impose a specific outcome on others and if no agreement is reached all players receive a predetermined status quo outcome. Bargaining games have been studied from a variety of fields, including game theory, economics, psychology and simulation based methods like genetic algorithms. In this work we extend the analysis by means of deep multi-agent reinforcement learning (MARL). To study the dynamics of bargaining with reinforcement learning we propose two different bargaining environments which display the following situations: in the first domain two agents have to agree on the division of an asset, e.g., the division of a fixed amount of money between each other. The second domain models a seller-buyer scenario in which agents must agree on a price for a product. We empirica lly demonstrate that the bargaining result under MARL is influenced by agents' risk-aversion as well as information asymmetry between agents.}, language = {en} } @inproceedings{PhanBelznerKiermeieretal.2019, author = {Phan, Thomy and Belzner, Lenz and Kiermeier, Marie and Friedrich, Markus and Schmid, Kyrill and Linnhoff-Popien, Claudia}, title = {Memory Bounded Open-Loop Planning in Large POMDPs Using Thompson Sampling}, volume = {33}, booktitle = {AAAI-19 / IAAI-19 / EAAI-20 Proceedings}, number = {1}, publisher = {AAAI Press}, address = {Palo Alto}, issn = {2374-3468}, doi = {https://doi.org/10.1609/aaai.v33i01.33017941}, pages = {7941 -- 7948}, year = {2019}, language = {en} } @inproceedings{PhanSchmidBelzneretal.2019, author = {Phan, Thomy and Schmid, Kyrill and Belzner, Lenz and Gabor, Thomas and Feld, Sebastian and Linnhoff-Popien, Claudia}, title = {Distributed Policy Iteration for Scalable Approximation of Cooperative Multi-Agent Policies}, booktitle = {AAMAS '19 : Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems}, publisher = {International Foundation for Autonomous Agents and Multiagent Systems}, address = {Richland}, isbn = {978-1-4503-6309-9}, url = {https://www.ifaamas.org/Proceedings/aamas2019/forms/contents.htm}, pages = {2162 -- 2164}, year = {2019}, language = {en} } @inproceedings{SchmidBelznerKiermeieretal.2018, author = {Schmid, Kyrill and Belzner, Lenz and Kiermeier, Marie and Neitz, Alexander and Phan, Thomy and Gabor, Thomas and Linnhoff-Popien, Claudia}, title = {Risk-sensitivity in simulation based online planning}, booktitle = {KI 2018: Advances in Artificial Intelligence : Proceedings}, editor = {Trollmann, Frank and Turhan, Anni-Yasmin}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-00111-7}, doi = {https://doi.org/10.1007/978-3-030-00111-7_20}, pages = {229 -- 240}, year = {2018}, language = {en} } @inproceedings{GaborBelznerPhanetal.2018, author = {Gabor, Thomas and Belzner, Lenz and Phan, Thomy and Schmid, Kyrill}, title = {Preparing for the unexpected}, booktitle = {Proceedings : 15th IEEE International Conference on Autonomic Computing - ICAC 2018}, subtitle = {diversity improves planning resilience in evolutionary algorithms}, publisher = {IEEE}, address = {Los Alamitos (CA)}, isbn = {978-1-5386-5139-1}, issn = {2474-0756}, doi = {https://doi.org/10.1109/ICAC.2018.00023}, pages = {131 -- 140}, year = {2018}, language = {en} } @inproceedings{SchmidBelznerGaboretal.2018, author = {Schmid, Kyrill and Belzner, Lenz and Gabor, Thomas and Phan, Thomy}, title = {Action markets in deep multi-agent reinforcement learning}, booktitle = {Artificial Neural Networks and Machine Learning - ICANN 2018 : Proceedings, Part II}, editor = {Kurkova, Vera and Manolopoulos, Yannis and Hammer, Barbara and Iliadis, Lazaros and Maglogiannis, Ilias}, publisher = {Springer}, address = {Cham}, isbn = {978-3-030-01421-6}, doi = {https://doi.org/10.1007/978-3-030-01421-6_24}, pages = {240 -- 249}, year = {2018}, language = {en} } @inproceedings{PhanBelznerGaboretal.2018, author = {Phan, Thomy and Belzner, Lenz and Gabor, Thomas and Schmid, Kyrill}, title = {Leveraging statistical multi-agent online planning with emergent value function approximation}, booktitle = {AAMAS '18: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems}, publisher = {International Foundation for Autonomous Agents and MultiAgent Systems (IFAAMAS)}, address = {Richland}, isbn = {978-1-4503-5649-7}, issn = {2523-5699}, url = {https://www.ifaamas.org/Proceedings/aamas2018/forms/contents.htm\#18}, pages = {730 -- 738}, year = {2018}, language = {en} } @inproceedings{SchmidBelznerMuelleretal.2021, author = {Schmid, Kyrill and Belzner, Lenz and M{\"u}ller, Robert and Tochtermann, Johannes and Linnhoff-Popien, Claudia}, title = {Stochastic market games}, booktitle = {Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence}, publisher = {IJCAI}, address = {[s. l.]}, isbn = {978-0-9992411-9-6}, doi = {https://doi.org/10.24963/ijcai.2021/54}, pages = {384 -- 390}, year = {2021}, language = {en} } @inproceedings{SunPierothSchmidetal.2022, author = {Sun, Xiyue and Pieroth, Fabian Raoul and Schmid, Kyrill and Wirsing, Martin and Belzner, Lenz}, title = {On Learning Stable Cooperation in the Iterated Prisoner's Dilemma with Paid Incentives}, booktitle = {Proceedings: 2022 IEEE 42nd International Conference on Distributed Computing Systems Workshops: ICDCSW 2022}, publisher = {IEEE}, address = {Los Alamitos}, isbn = {978-1-6654-8879-2}, issn = {2332-5666}, doi = {https://doi.org/10.1109/ICDCSW56584.2022.00031}, pages = {113 -- 118}, year = {2022}, 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} }