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 - 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 - Linnhoff-Popien, Claudia ED - Aguirre, Hernan T1 - Inheritance-based diversity measures for explicit convergence control in evolutionary algorithms T2 - GECCO '18: Proceedings of the 2018 Genetic and Evolutionary Computation Conference UR - https://doi.org/10.1145/3205455.3205630 KW - diversity KW - evolutionary algorithms KW - premature convergence KW - optimization KW - genetic drift Y1 - 2018 UR - https://doi.org/10.1145/3205455.3205630 SN - 978-1-4503-5618-3 SP - 841 EP - 848 PB - ACM CY - New York ER - TY - JOUR A1 - Gabor, Thomas A1 - Illium, Steffen A1 - Zorn, Maximilian A1 - Lenta, Cristian A1 - Mattausch, Andy A1 - Belzner, Lenz A1 - Linnhoff-Popien, Claudia T1 - Self-Replication in Neural Networks JF - Artificial Life UR - https://doi.org/10.1162/artl_a_00359 KW - neural network KW - self-replication KW - artificial chemistry system KW - soup KW - weight space Y1 - 2022 UR - https://doi.org/10.1162/artl_a_00359 SN - 1530-9185 VL - 28 IS - 2 SP - 205 EP - 223 PB - MIT Press CY - Cambridge 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 - TY - CHAP A1 - Schmid, Kyrill A1 - Belzner, Lenz A1 - Müller, Robert A1 - Tochtermann, Johannes A1 - Linnhoff-Popien, Claudia T1 - Stochastic market games T2 - Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence UR - https://doi.org/10.24963/ijcai.2021/54 Y1 - 2021 UR - https://doi.org/10.24963/ijcai.2021/54 SN - 978-0-9992411-9-6 SP - 384 EP - 390 PB - IJCAI CY - [s. l.] ER -