Publications

2026

Phan, Thomy
Towards Streamlined Learning and Search for Multi-Agent Optimization
Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence (IJCAI-ECAI 2026)
Bremen, Germany , 2026. - page 8179-8184
doi:10.24963/ijcai.2026/909 ...

Altmann, Philipp; Zorn, Maximilian; Koenig, Sven; Phan, Thomy
Dynamic Reward Incentives for Emergent Cooperation under Changing Rewards
in Transactions on Machine Learning Research (2026)
https://openreview.net/pdf?id=9Ltu1HV2YI

Phan, Thomy; Driscoll, Joseph; Romberg, Justin; Koenig, Sven
Confidence-Based Curricula for Multi-Agent Path Finding via Reinforcement Learning
in Autonomous Agents and Multi-Agent Systems volume 40 (2026)
doi:10.1007/s10458-026-09747-7 ...

Phan, Thomy; Koenig, Sven
Spatially Grouped Curriculum Learning for Multi-Agent Path Finding
in Proceedings of the AAAI Conference on Artificial Intelligence volume 40 (2026) issue 35. - page 29642-29650
doi:10.1609/aaai.v40i35.40208 ...

Phan, Thomy; Chan, Shao-Hung; Koenig, Sven
Truncated Counterfactual Learning for Anytime Multi-Agent Path Finding
in Proceedings of the AAAI Conference on Artificial Intelligence volume 40 (2026) issue 35. - page 29633-29641
doi:10.1609/aaai.v40i35.40207 ...

2025

Phan, Thomy; Zhang, Benran; Chan, Shao-Hung; Koenig, Sven
Anytime Multi-Agent Path Finding with an Adaptive Delay-Based Heuristic
in Proceedings of the AAAI Conference on Artificial Intelligence volume 39 (2025) issue 22. - page 23286-23294
doi:10.1609/aaai.v39i22.34495 ...
39th AAAI Conference on Artificial Intelligence (AAAI), Philadelphia, Pennsylvania, USA

Phan, Thomy; Chan, Shao-Hung; Koenig, Sven
Counterfactual Online Learning for Open-Loop Monte-Carlo Planning
in Proceedings of the AAAI Conference on Artificial Intelligence volume 39 (2025) issue 25. - page 26651-26658
doi:10.1609/aaai.v39i25.34867 ...
39th AAAI Conference on Artificial Intelligence (AAAI), Philadelphia, Pennsylvania, USA

Phan, Thomy; Phan, Timy; Koenig, Sven
Generative Curricula for Multi-Agent Path Finding via Unsupervised and Reinforcement Learning
in Journal of Artificial Intelligence Research volume 82 (2025) . - page 2471-2534
doi:10.1613/jair.1.17403 ...

Chan, Shao-Hung; Phan, Thomy; Li, Jiaoyang; Koenig, Sven
New Mechanisms in Flex Distribution for Bounded Suboptimal Multi-Agent Path Finding
Proceedings of the Eighteenth International Symposium on Combinatorial Search
Washington, DC, USA : AAAI Press, 2025. - page 47-55
doi:10.1609/socs.v18i1.35975 ...

2024

Phan, Thomy; Huang, Taoan; Dilkina, Bistra; Koenig, Sven
Adaptive Anytime Multi-Agent Path Finding Using Bandit-Based Large Neighborhood Search
in Proceedings of the AAAI Conference on Artificial Intelligence volume 38 (2024) issue 16. - page 17514-17522
doi:10.1609/aaai.v38i16.29701 ...
38th AAAI Conference on Artificial Intelligence (AAAI), Vancouver, Canada

Chan, Shao-Hung; Chen, Zhe; Lin, Dian-Lun; Zhang, Yue; Harabor, Daniel; Koenig, Sven; Huang, Tsung-Wei; Phan, Thomy
Anytime Multi-Agent Path Finding using Operation Parallelism in Large Neighborhood Search
Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS '24)
Richland, SC : International Foundation for Autonomous Agents and Multiagent Systems, 2024. - page 2183-2185 . - (ACM Conferences)
doi:10.5555/3635637.3663101 ...

Phan, Thomy; Driscoll, Joseph; Romberg, Justin; Koenig, Sven
Confidence-Based Curriculum Learning for Multi-Agent Path Finding
Proceedings of the 23rd International Conference on Autonomous Agents and Multiagent Systems (AAMAS '24)
Richland, SC : International Foundation for Autonomous Agents and Multiagent Systems, 2024. - page 1558-1566 . - (ACM Conferences)
doi:10.5555/3635637.3663016 ...

Phan, Thomy; Sommer, Felix; Ritz, Fabian; Altmann, Philipp; Nüßlein, Jonas; Kölle, Michael; Belzner, Lenz; Linnhoff-Popien, Claudia
Emergent Cooperation from Mutual Acknowledgment Exchange in Multi-Agent Reinforcement Learning
in Autonomous Agents and Multi-Agent Systems volume 38 (2024)
doi:10.1007/s10458-024-09666-5 ...

2023

Phan, Thomy
Emergence and Resilience in Multi-Agent Reinforcement Learning
München, Ludwig-Maximilians-Universität, 2023. - XIV, 69 page
doi:10.5282/edoc.31981 ...
(dissertation, 2023, )

Phan, Thomy; Ritz, Fabian; Altmann, Philipp; Zorn, Maximilian; Nüßlein, Jonas; Kölle, Michael; Gabor, Thomas; Linnhoff-Popien, Claudia
Attention-Based Recurrence for Multi-Agent Reinforcement Learning under Stochastic Partial Obse ...
Proceedings of the 40th International Conference on Machine Learning
Red Hook, NY : Curran Associates, Inc., 2023. - page 27840-27853 . - (Proceedings of Machine Learning Research; 202)
https://proceedings.mlr.press/v202/phan23a.html

Altmann, Philipp; Ritz, Fabian; Feuchtinger, Leonard; Nüßlein, Jonas; Linnhoff-Popien, Claudia; Phan, Thomy
CROP: Towards Distributional-Shift Robust Reinforcement Learning Using Compact Reshaped Observa ...
Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence (IJCAI-23)
Vienna, Austria : International Joint Conferences on Artificial Intelligence Organization, 2023. - page 3414-3422
doi:10.24963/ijcai.2023/380 ...

2022

Phan, Thomy; Sommer, Felix; Altmann, Philipp; Ritz, Fabian; Belzner, Lenz; Linnhoff-Popien, Claudia
Emergent Cooperation from Mutual Acknowledgment Exchange
Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems (AAMAS '22)
Richland, SC : International Foundation for Autonomous Agents and Multiagent Systems, 2022. - page 1047-1055 . - (ACM Conferences)
doi:10.5555/3535850.3535967 ...

Müller, Robert; Illium, Steffen; Phan, Thomy; Haider, Tom; Linnhoff-Popien, Claudia
Towards Anomaly Detection in Reinforcement Learning
Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems (AAMAS '22)
Richland, SC : International Foundation for Autonomous Agents and Multiagent Systems, 2022. - page 1799-1803 . - (ACM Conferences)
doi:10.5555/3535850.3536113 ...

2021

Phan, Thomy; Belzner, Lenz; Gabor, Thomas; Sedlmeier, Andreas; Ritz, Fabian; Linnhoff-Popien, Claudia
Resilient Multi-Agent Reinforcement Learning with Adversarial Value Decomposition
in Proceedings of the AAAI Conference on Artificial Intelligence volume 35 (2021) issue 13. - page 11308-11316
doi:10.1609/aaai.v35i13.17348 ...
35th AAAI Conference on Artificial Intelligence (AAAI), Online

Phan, Thomy; Ritz, Fabian; Belzner, Lenz; Altmann, Philipp; Gabor, Thomas; Linnhoff-Popien, Claudia
VAST: Value Function Factorization with Variable Agent Sub-Teams
Proceedings of the 35th Conference on Neural Information Processing Systems (NeurIPS 2021)
Red Hook, NY : Curran Associates, Inc., 2021. - page 24018-24032 . - (Advances in Neural Information Processing Systems; 34)
https://proceedings.neurips.cc/paper_files/paper/2 ...

2020

Phan, Thomy; Gabor, Thomas; Sedlmeier, Andreas; Ritz, Fabian; Kempter, Bernhard; Klein, Cornel; Sauer, Horst; Schmid, Reiner; Wieghardt, Jan; Zeller, Marc; Linnhoff-Popien, Claudia
Learning and Testing Resilience in Cooperative Multi-Agent Systems
Proceedings of the 19th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS '20)
Richland, SC : International Foundation for Autonomous Agents and Multiagent Systems, 2020. - page 1055-1063 . - (ACM Conferences)
doi:10.5555/3398761.3398884 ...

2019

Phan, Thomy; Gabor, Thomas; Müller, Robert; Roch, Christoph; Linnhoff-Popien, Claudia
Adaptive Thompson Sampling Stacks for Memory Bounded Open-Loop Planning
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19)
s.l. : International Joint Conferences on Artificial Intelligence Organization, 2019. - page 5607-5613
doi:10.24963/ijcai.2019/778 ...

Phan, Thomy; Schmid, Kyrill; Belzner, Lenz; Gabor, Thomas; Feld, Sebastian; Linnhoff-Popien, Claudia
Distributed Policy Iteration for Scalable Approximation of Cooperative Multi-Agent Policies
Proceedings of the 18th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS '19)
Richland, SC : International Foundation for Autonomous Agents and Multiagent Systems, 2019. - page 2162-2164 . - (ACM Conferences)
doi:10.5555/3306127.3332044 ...

Phan, Thomy; Belzner, Lenz; Kiermeier, Marie; Friedrich, Markus; Schmid, Kyrill; Linnhoff-Popien, Claudia
Memory Bounded Open-Loop Planning in Large POMDPs Using Thompson Sampling
in Proceedings of the AAAI Conference on Artificial Intelligence volume 33 (2019) issue 1. - page 7941-7948
doi:10.1609/aaai.v33i01.33017941 ...
33rd AAAI Conference on Artificial Intelligence (AAAI), Honolulu, Hawaii, USA

Gabor, Thomas; Sedlmeier, Andreas; Kiermeier, Marie; Phan, Thomy; Henrich, Marcel; Pichlmair, Monika; Kempter, Bernhard; Klein, Cornel; Sauer, Horst; Schmid, Reiner; Wieghardt, Jan
Scenario Co-Evolution for Reinforcement Learning on a Grid World Smart Factory Domain
Proceedings of the Genetic and Evolutionary Computation Conference
New York, NY, USA : Association for Computing Machinery, 2019. - page 898-906 . - (ACM Conferences)
doi:10.1145/3321707.3321831 ...

Gabor, Thomas; Peter, Jan; Phan, Thomy; Meyer, Christian; Linnhoff-Popien, Claudia
Subgoal-Based Temporal Abstraction in Monte-Carlo Tree Search
Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19)
s.l. : International Joint Conferences on Artificial Intelligence Organization, 2019. - page 5562-5568
doi:10.24963/ijcai.2019/772 ...

2018

Phan, Thomy; Belzner, Lenz; Gabor, Thomas; Schmid, Kyrill
Leveraging Statistical Multi-Agent Online Planning with Emergent Value Function Approximation
Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems (AAMAS '18)
Richland,SC : International Foundation for Autonomous Agents and Multiagent Systems, 2018. - page 730-738 . - (ACM Conferences)
doi:10.5555/3237383.3237491 ...