TY - CHAP A1 - Ritz, Fabian A1 - Ratke, Daniel A1 - Phan, Thomy A1 - Belzner, Lenz A1 - Linnhoff-Popien, Claudia T1 - A sustainable ecosystem through emergent cooperation in multi-agent reinforcement learning T2 - Proceedings of the Artificial Life Conference 2021 UR - https://doi.org/10.1162/isal_a_00399 Y1 - 2021 UR - https://doi.org/10.1162/isal_a_00399 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-12975 VL - 2021 PB - MIT Press CY - Cambridge ER - TY - CHAP A1 - Phan, Thomy A1 - Ritz, Fabian A1 - Belzner, Lenz A1 - Altmann, Philipp A1 - Gabor, Thomas A1 - Linnhoff-Popien, Claudia T1 - VAST: Value Function Factorization with Variable Agent Sub-Teams T2 - Advances in Neural Information Processing Systems 34 (NeurIPS 2021) KW - Multi-Agent Learning KW - Reinforcement Learning KW - Value Function Factorization Y1 - 2021 UR - https://proceedings.neurips.cc/paper/2021/hash/c97e7a5153badb6576d8939469f58336-Abstract.html PB - Neural Information Processing Systems Foundation, Inc. (NIPS) ER - TY - CHAP A1 - Phan, Thomy A1 - Sommer, Felix A1 - Altmann, Philipp A1 - Ritz, Fabian A1 - Belzner, Lenz A1 - Linnhoff-Popien, Claudia T1 - Emergent Cooperation from Mutual Acknowledgment Exchange T2 - AAMAS '22: Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems UR - https://dl.acm.org/doi/10.5555/3535850.3535967 KW - multi-agent learning KW - reinforcement learning KW - mutual acknowledgments KW - peer incentivization KW - emergent cooperation Y1 - 2022 UR - https://dl.acm.org/doi/10.5555/3535850.3535967 SN - 978-1-4503-9213-6 SP - 1047 EP - 1055 PB - International Foundation for Autonomous Agents and Multiagent Systems CY - Richland ER - TY - CHAP A1 - Phan, Thomy A1 - Belzner, Lenz A1 - Kiermeier, Marie A1 - Friedrich, Markus A1 - Schmid, Kyrill A1 - Linnhoff-Popien, Claudia T1 - Memory Bounded Open-Loop Planning in Large POMDPs Using Thompson Sampling T2 - AAAI-19 / IAAI-19 / EAAI-20 Proceedings UR - https://doi.org/10.1609/aaai.v33i01.33017941 Y1 - 2019 UR - https://doi.org/10.1609/aaai.v33i01.33017941 SN - 2374-3468 VL - 33 IS - 1 SP - 7941 EP - 7948 PB - AAAI Press CY - Palo Alto ER - TY - CHAP A1 - Hahn, Carsten A1 - Phan, Thomy A1 - Gabor, Thomas A1 - Belzner, Lenz A1 - Linnhoff-Popien, Claudia T1 - Emergent Escape-based Flocking behavior using Multi-Agent Reinforcement Learning T2 - Artificial Life Conference Proceedings UR - https://doi.org/10.1162/isal_a_00226 Y1 - 2019 UR - https://doi.org/10.1162/isal_a_00226 SP - 598 EP - 605 PB - MIT Press CY - Cambridge ER - TY - CHAP A1 - Phan, Thomy A1 - Schmid, Kyrill A1 - Belzner, Lenz A1 - Gabor, Thomas A1 - Feld, Sebastian A1 - Linnhoff-Popien, Claudia T1 - Distributed Policy Iteration for Scalable Approximation of Cooperative Multi-Agent Policies T2 - AAMAS '19: Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems KW - multi-agent planning KW - multi-agent learning KW - policy iteration Y1 - 2019 UR - https://www.ifaamas.org/Proceedings/aamas2019/forms/contents.htm SN - 978-1-4503-6309-9 SP - 2162 EP - 2164 PB - International Foundation for Autonomous Agents and Multiagent Systems CY - Richland ER - TY - JOUR A1 - Sedlmeier, Andreas A1 - Gabor, Thomas A1 - Phan, Thomy A1 - Belzner, Lenz T1 - Uncertainty-Based Out-of-Distribution Detection in Deep Reinforcement Learning JF - Digitale Welt UR - https://doi.org/10.1007/s42354-019-0238-z Y1 - 2019 UR - https://doi.org/10.1007/s42354-019-0238-z SN - 2569-1996 VL - 4 IS - 1 SP - 74 EP - 78 PB - Digitale Welt Academy CY - München ER - TY - CHAP A1 - Phan, Thomy A1 - Belzner, Lenz A1 - Gabor, Thomas A1 - Sedlmeier, Andreas A1 - Ritz, Fabian A1 - Linnhoff-Popien, Claudia T1 - Resilient multi-agent reinforcement learning with adversarial value decomposition T2 - AAAI-21 / IAAI-21 / EAAI-21 Proceedings UR - https://ojs.aaai.org/index.php/AAAI/article/view/17348 KW - Multiagent Learning KW - Adversarial Learning & Robustness KW - Adversarial Agents KW - Reinforcement Learning Y1 - 2021 UR - https://ojs.aaai.org/index.php/AAAI/article/view/17348 SN - 978-1-57735-866-4 SN - 2374-3468 VL - 35 IS - 13 SP - 11308 EP - 11316 PB - AAAI Press CY - Palo Alto (CA) ER - TY - JOUR A1 - Gabor, Thomas A1 - Sedlmeier, Andreas A1 - Phan, Thomy A1 - Ritz, Fabian A1 - Kiermeier, Marie A1 - Belzner, Lenz A1 - Kempter, Bernhard A1 - Klein, Cornel A1 - Sauer, Horst A1 - Schmid, Reiner A1 - Wieghardt, Jan A1 - Zeller, Marc A1 - Linnhoff-Popien, Claudia T1 - The scenario coevolution paradigm BT - adaptive quality assurance for adaptive systems JF - International Journal on Software Tools for Technology Transfer N2 - 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). UR - https://doi.org/10.1007/s10009-020-00560-5 Y1 - 2020 UR - https://doi.org/10.1007/s10009-020-00560-5 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-13929 SN - 1433-2787 VL - 22 IS - 4 SP - 457 EP - 476 PB - Springer CY - Berlin ER - TY - CHAP A1 - Gabor, Thomas A1 - Sünkel, Leo A1 - Ritz, Fabian A1 - Phan, Thomy A1 - Belzner, Lenz A1 - Roch, Christoph A1 - Feld, Sebastian A1 - Linnhoff-Popien, Claudia T1 - The Holy Grail of Quantum Artificial Intelligence: Major Challenges in Accelerating the Machine Learning Pipeline T2 - ICSEW'20 : Proceedings of the IEEE/ACM 42nd International Conference on Software Engineering Workshops UR - https://doi.org/10.1145/3387940.3391469 KW - quantum computing KW - artificial intelligence KW - software engineering Y1 - 2020 UR - https://doi.org/10.1145/3387940.3391469 SN - 978-1-4503-7963-2 SP - 456 EP - 461 PB - ACM CY - New York ER - TY - CHAP A1 - Schmid, Kyrill A1 - Belzner, Lenz A1 - Gabor, Thomas A1 - Phan, Thomy ED - Kurkova, Vera ED - Manolopoulos, Yannis ED - Hammer, Barbara ED - Iliadis, Lazaros ED - Maglogiannis, Ilias T1 - Action Markets in Deep Multi-Agent Reinforcement Learning T2 - Artificial Neural Networks and Machine Learning – ICANN 2018: 27th International Conference on Artificial Neural Networks Proceedings, Part II UR - https://doi.org/10.1007/978-3-030-01421-6_24 Y1 - 2018 UR - https://doi.org/10.1007/978-3-030-01421-6_24 SN - 978-3-030-01421-6 SN - 978-3-030-01420-9 SP - 240 EP - 249 PB - Springer CY - Cham ER - TY - CHAP A1 - Schmid, Kyrill A1 - Belzner, Lenz A1 - Kiermeier, Marie A1 - Neitz, Alexander A1 - Phan, Thomy A1 - Gabor, Thomas A1 - Linnhoff-Popien, Claudia ED - Trollmann, Frank ED - Turhan, Anni-Yasmin T1 - Risk-Sensitivity in Simulation Based Online Planning T2 - KI 2018: Advances in Artificial Intelligence: 41st German Conference on AI Proceedings UR - https://doi.org/10.1007/978-3-030-00111-7_20 KW - online planning KW - risk-sensitivity KW - local planning Y1 - 2018 UR - https://doi.org/10.1007/978-3-030-00111-7_20 SN - 978-3-030-00111-7 SN - 978-3-030-00110-0 SP - 229 EP - 240 PB - Springer CY - Cham ER - TY - CHAP A1 - Gabor, Thomas A1 - Belzner, Lenz A1 - Phan, Thomy A1 - Schmid, Kyrill T1 - Preparing for the Unexpected: Diversity Improves Planning Resilience in Evolutionary Algorithms T2 - Proceedings: 15th IEEE International Conference on Autonomic Computing - ICAC 2018 UR - https://doi.org/10.1109/ICAC.2018.00023 KW - planning KW - unexpected events KW - dynamic fitness KW - resilience KW - robustness KW - self-protection KW - self-healing KW - diversity KW - optimization KW - evolutionary algorithms Y1 - 2018 UR - https://doi.org/10.1109/ICAC.2018.00023 SN - 978-1-5386-5139-1 SN - 2474-0756 SP - 131 EP - 140 PB - IEEE CY - Los Alamitos ER - TY - CHAP A1 - Phan, Thomy A1 - Belzner, Lenz A1 - Gabor, Thomas A1 - Schmid, Kyrill T1 - Leveraging statistical multi-agent online planning with emergent value function approximation T2 - AAMAS '18: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems KW - multi-agent planning KW - online planning KW - value function approximation Y1 - 2018 UR - https://www.ifaamas.org/Proceedings/aamas2018/forms/contents.htm#18 SN - 978-1-4503-5649-7 SN - 2523-5699 SP - 730 EP - 738 PB - International Foundation for Autonomous Agents and MultiAgent Systems (IFAAMAS) CY - Richland ER - TY - CHAP A1 - Belzner, Lenz A1 - Schmid, Kyrill A1 - Phan, Thomy A1 - Gabor, Thomas A1 - Wirsing, Martin ED - Margaria, Tiziana ED - Steffen, Bernhard T1 - The Sharer’s Dilemma in Collective Adaptive Systems of Self-interested Agents T2 - Leveraging Applications of Formal Methods, Verification and Validation, Distributed Systems, 8th International Symposium, ISoLA 2018, Limassol, Cyprus, November 5–9, 2018, Proceedings, Part III UR - https://doi.org/10.1007/978-3-030-03424-5_16 Y1 - 2018 UR - https://doi.org/10.1007/978-3-030-03424-5_16 SN - 978-3-030-03423-8 SN - 978-3-030-03424-5 SP - 241 EP - 256 PB - Springer CY - Cham ER - TY - JOUR A1 - Phan, Thomy A1 - Sommer, Felix A1 - Ritz, Fabian A1 - Altmann, Philipp A1 - Nüßlein, Jonas A1 - Kölle, Michael A1 - Belzner, Lenz A1 - Linnhoff-Popien, Claudia T1 - Emergent cooperation from mutual acknowledgment exchange in multi-agent reinforcement learning JF - Autonomous Agents and Multi-Agent Systems N2 - 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. UR - https://doi.org/10.1007/s10458-024-09666-5 Y1 - 2024 UR - https://doi.org/10.1007/s10458-024-09666-5 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-49287 SN - 1573-7454 SN - 1387-2532 VL - 38 IS - 2 PB - Springer CY - Dordrecht ER - TY - INPR A1 - Phan, Thomy A1 - Sommer, Felix A1 - Ritz, Fabian A1 - Altmann, Philipp A1 - Nüßlein, Jonas A1 - Kölle, Michael A1 - Belzner, Lenz A1 - Linnhoff-Popien, Claudia T1 - Emergent Cooperation from Mutual Acknowledgment Exchange in Multi-Agent Reinforcement Learning T2 - Research Square N2 - 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. UR - https://doi.org/10.21203/rs.3.rs-2315844/v1 Y1 - 2022 UR - https://doi.org/10.21203/rs.3.rs-2315844/v1 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-45471 SN - 2693-5015 PB - Research Square CY - Durham ER - TY - CHAP A1 - Sedlmeier, Andreas A1 - Gabor, Thomas A1 - Phan, Thomy A1 - Belzner, Lenz A1 - Linnhoff-Popien, Claudia ED - Rocha, Ana Paula ED - Steels, Luc ED - Herik, Jaap van den T1 - Uncertainty-based out-of-distribution classification in deep reinforcement learning T2 - Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 2: ICAART N2 - 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. UR - https://doi.org/10.5220/0008949905220529 KW - Uncertainty in AI KW - Out-of-Distribution Classification KW - Deep Reinforcement Learning Y1 - 2020 UR - https://doi.org/10.5220/0008949905220529 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-13959 SN - 978-989-758-395-7 SN - 2184-433X SP - 522 EP - 529 PB - SciTePress CY - Setúbal ER - TY - CHAP A1 - Schmid, Kyrill A1 - Belzner, Lenz A1 - Phan, Thomy A1 - Gabor, Thomas A1 - Linnhoff-Popien, Claudia ED - Rocha, Ana Paula ED - Steels, Luc ED - Herik, Jaap van den T1 - Multi-agent reinforcement learning for bargaining under risk and asymmetric information T2 - Proceedings of the 12th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART 2020 N2 - 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. UR - https://doi.org/10.5220/0008913901440151 Y1 - 2020 UR - https://doi.org/10.5220/0008913901440151 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-13945 SN - 978-989-758-395-7 SN - 2184-433X SP - 144 EP - 151 PB - SciTePress CY - Setúbal ER -