@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{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{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{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{HahnPhanGaboretal.2019, author = {Hahn, Carsten and Phan, Thomy and Gabor, Thomas and Belzner, Lenz and Linnhoff-Popien, Claudia}, title = {Emergent Escape-based Flocking behavior using Multi-Agent Reinforcement Learning}, pages = {isal_a_00226}, booktitle = {Artificial Life Conference Proceedings}, publisher = {MIT Press}, address = {Cambridge}, doi = {https://doi.org/10.1162/isal_a_00226}, pages = {598 -- 605}, 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} } @article{SedlmeierGaborPhanetal.2019, author = {Sedlmeier, Andreas and Gabor, Thomas and Phan, Thomy and Belzner, Lenz}, title = {Uncertainty-Based Out-of-Distribution Detection in Deep 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/s42354-019-0238-z}, pages = {74 -- 78}, year = {2019}, language = {en} } @inproceedings{PhanBelznerGaboretal.2021, author = {Phan, Thomy and Belzner, Lenz and Gabor, Thomas and Sedlmeier, Andreas and Ritz, Fabian and Linnhoff-Popien, Claudia}, title = {Resilient multi-agent reinforcement learning with adversarial value decomposition}, volume = {35}, booktitle = {AAAI-21 / IAAI-21 / EAAI-21 Proceedings}, number = {13}, publisher = {AAAI Press}, address = {Palo Alto (CA)}, isbn = {978-1-57735-866-4}, issn = {2374-3468}, doi = {https://ojs.aaai.org/index.php/AAAI/article/view/17348}, pages = {11308 -- 11316}, year = {2021}, language = {en} } @article{GaborSedlmeierPhanetal.2020, author = {Gabor, Thomas and Sedlmeier, Andreas and Phan, Thomy and Ritz, Fabian and Kiermeier, Marie and Belzner, Lenz and Kempter, Bernhard and Klein, Cornel and Sauer, Horst and Schmid, Reiner and Wieghardt, Jan and Zeller, Marc and Linnhoff-Popien, Claudia}, title = {The scenario coevolution paradigm}, volume = {22}, journal = {International Journal on Software Tools for Technology Transfer}, subtitle = {adaptive quality assurance for adaptive systems}, number = {4}, publisher = {Springer}, address = {Berlin}, issn = {1433-2787}, doi = {https://doi.org/10.1007/s10009-020-00560-5}, pages = {457 -- 476}, year = {2020}, abstract = {Systems are becoming increasingly more adaptive, using techniques like machine learning to enhance their behavior on their own rather than only through human developers programming them. We analyze the impact the advent of these new techniques has on the discipline of rigorous software engineering, especially on the issue of quality assurance. To this end, we provide a general description of the processes related to machine learning and embed them into a formal framework for the analysis of adaptivity, recognizing that to test an adaptive system a new approach to adaptive testing is necessary. We introduce scenario coevolution as a design pattern describing how system and test can work as antagonists in the process of software evolution. While the general pattern applies to large-scale processes (including human developers further augmenting the system), we show all techniques on a smaller-scale example of an agent navigating a simple smart factory. We point out new aspects in software engineering for adaptive systems that may be tackled naturally using scenario coevolution. This work is a substantially extended take on Gabor et al. (International symposium on leveraging applications of formal methods, Springer, pp 137-154, 2018).}, language = {en} } @inproceedings{GaborSuenkelRitzetal.2020, author = {Gabor, Thomas and S{\"u}nkel, Leo and Ritz, Fabian and Phan, Thomy and Belzner, Lenz and Roch, Christoph and Feld, Sebastian and Linnhoff-Popien, Claudia}, title = {The Holy Grail of Quantum Artificial Intelligence: Major Challenges in Accelerating the Machine Learning Pipeline}, booktitle = {ICSEW'20 : Proceedings of the IEEE/ACM 42nd International Conference on Software Engineering Workshops}, publisher = {ACM}, address = {New York}, isbn = {978-1-4503-7963-2}, doi = {https://doi.org/10.1145/3387940.3391469}, pages = {456 -- 461}, year = {2020}, 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: 27th International Conference on Artificial Neural Networks 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{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: 41st German Conference on AI 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: Diversity Improves Planning Resilience in Evolutionary Algorithms}, booktitle = {Proceedings: 15th IEEE International Conference on Autonomic Computing - ICAC 2018}, publisher = {IEEE}, address = {Los Alamitos}, 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{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{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}, editor = {Margaria, Tiziana and Steffen, Bernhard}, 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} } @article{PhanSommerRitzetal.2024, author = {Phan, Thomy and Sommer, Felix and Ritz, Fabian and Altmann, Philipp and N{\"u}ßlein, Jonas and K{\"o}lle, Michael and Belzner, Lenz and Linnhoff-Popien, Claudia}, title = {Emergent cooperation from mutual acknowledgment exchange in multi-agent reinforcement learning}, volume = {38}, pages = {34}, journal = {Autonomous Agents and Multi-Agent Systems}, number = {2}, publisher = {Springer}, address = {Dordrecht}, issn = {1573-7454}, doi = {https://doi.org/10.1007/s10458-024-09666-5}, year = {2024}, abstract = {Peer incentivization (PI) is a recent approach where all agents learn to reward or penalize each other in a distributed fashion, which often leads to emergent cooperation. Current PI mechanisms implicitly assume a flawless communication channel in order to exchange rewards. These rewards are directly incorporated into the learning process without any chance to respond with feedback. Furthermore, most PI approaches rely on global information, which limits scalability and applicability to real-world scenarios where only local information is accessible. In this paper, we propose Mutual Acknowledgment Token Exchange (MATE), a PI approach defined by a two-phase communication protocol to exchange acknowledgment tokens as incentives to shape individual rewards mutually. All agents condition their token transmissions on the locally estimated quality of their own situations based on environmental rewards and received tokens. MATE is completely decentralized and only requires local communication and information. We evaluate MATE in three social dilemma domains. Our results show that MATE is able to achieve and maintain significantly higher levels of cooperation than previous PI approaches. In addition, we evaluate the robustness of MATE in more realistic scenarios, where agents can deviate from the protocol and communication failures can occur. We also evaluate the sensitivity of MATE w.r.t. the choice of token values.}, language = {en} } @unpublished{PhanSommerRitzetal.2022, author = {Phan, Thomy and Sommer, Felix and Ritz, Fabian and Altmann, Philipp and N{\"u}ßlein, Jonas and K{\"o}lle, Michael and Belzner, Lenz and Linnhoff-Popien, Claudia}, title = {Emergent Cooperation from Mutual Acknowledgment Exchange in Multi-Agent Reinforcement Learning}, titleParent = {Research Square}, publisher = {Research Square}, address = {Durham}, doi = {https://doi.org/10.21203/rs.3.rs-2315844/v1}, year = {2022}, abstract = {Peer incentivization (PI) is a recent approach, where all agents learn to reward or to penalize each other in a distributed fashion which often leads to emergent cooperation. Current PI mechanisms implicitly assume a flawless communication channel in order to exchange rewards. These rewards are directly integrated into the learning process without any chance to respond with feedback. Furthermore, most PI approaches rely on global information which limits scalability and applicability to real-world scenarios, where only local information is accessible. In this paper, we propose Mutual Acknowledgment Token Exchange (MATE), a PI approach defined by a two-phase communication protocol to mutually exchange acknowledgment tokens to shape individual rewards. Each agent evaluates the monotonic improvement of its individual situation in order to accept or reject acknowledgment requests from other agents. MATE is completely decentralized and only requires local communication and information. We evaluate MATE in three social dilemma domains. Our results show that MATE is able to achieve and maintain significantly higher levels of cooperation than previous PI approaches. In addition, we evaluate the robustness of MATE in more realistic scenarios, where agents can defect from the protocol and where communication failures can occur. We also evaluate the sensitivity of MATE w.r.t. the choice of token values.}, language = {en} } @inproceedings{SedlmeierGaborPhanetal.2020, author = {Sedlmeier, Andreas and Gabor, Thomas and Phan, Thomy and Belzner, Lenz and Linnhoff-Popien, Claudia}, title = {Uncertainty-based out-of-distribution classification in deep reinforcement learning}, booktitle = {Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART}, editor = {Rocha, Ana Paula 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/10.5220/0008949905220529}, pages = {522 -- 529}, year = {2020}, abstract = {Robustness to out-of-distribution (OOD) data is an important goal in building reliable machine learning systems. As a first step towards a solution, we consider the problem of detecting such data in a value-based deep reinforcement learning (RL) setting. Modelling this problem as a one-class classification problem, we propose a framework for uncertainty-based OOD classification: UBOOD. It is based on the effect that an agent's epistemic uncertainty is reduced for situations encountered during training (in-distribution), and thus lower than for unencountered (OOD) situations. Being agnostic towards the approach used for estimating epistemic uncertainty, combinations with different uncertainty estimation methods, e.g. approximate Bayesian inference methods or ensembling techniques are possible. Evaluation shows that the framework produces reliable classification results when combined with ensemble-based estimators, while the combination with concrete dropout-based estimators fails to r eliably detect OOD situations.}, 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 Paula 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} }