Dr. Thomy Phan

Dr. Thomy Phan

Lehrstuhl für Mobile und Verteilte Systeme

Ludwig-Maximilians-Universität München, Institut für Informatik

Oettingenstraße 67
80538 München

Raum G004

Telefon: +49 89 / 2180-9167

Fax: +49 89 / 2180-9148

Mail: thomy.phan@ifi.lmu.de

Research Interests

❗For more information about my research, please visit my website

❗I have joined Sven Koenig’s Lab at University of Southern California in July 2023.

Teaching

Community

  • 26th European Conference on Artificial Intelligence (ECAI 2023): Program Committee
  • 37th Conference on Neural Information Processing Systems (NeurIPS 2023): Peer Review
  • 32nd International Joint Conference on Artificial Intelligence (IJCAI 2023): Program Committee (Main Track and AI & Social Good Track)
  • 40th International Conference on Machine Learning (ICML 2023): Peer Review
  • 22nd Conference on Autonomous Agents and Multiagent Systems (AAMAS 2023): Program Committee (BlueSky Ideas Track), Peer Review (Main Track)
  • 37th AAAI Conference on Artificial Intelligence (AAAI 2023): Program Committee
  • 36th Conference on Neural Information Processing Systems (NeurIPS 2022): Peer Review
  • 11th International Symposium On Leveraging Applications of Formal Methods (ISoLA 2022): Peer Review (Track – Rigorous Engineering of Collective Adaptive Systems)
  • 39th International Conference on Machine Learning (ICML 2022): Peer Review (Top 10%)
  • 36th AAAI Conference on Artificial Intelligence (AAAI 2022): Program Committee
  • PLOS ONE 2021: Peer Review
  • 35th AAAI Conference on Artificial Intelligence (AAAI 2021): Program Committee
  • International Journal on Software Tools for Technology Transfer (STTT REoCAS 2020): Peer Review
  • 1st International Symposium on Applied Artificial Intelligence (ISAAI 2019): Organizing Committee
  • 8th International Symposium On Leveraging Applications of Formal Methods (ISoLA 2018): Peer Review (Track – Rigorous Engineering of Collective Adaptive Systems)

Selected Publications

  • Thomy Phan, Fabian Ritz, Philipp Altmann, Maximilian Zorn, Jonas Nüßlein, Michael Kölle, Thomas Gabor, and Claudia Linnhoff-Popien, „Attention-Based Recurrence for Multi-Agent Reinforcement Learning under Stochastic Partial Observability“, in 40th International Conference on Machine Learning (ICML ’23), 2023, to appear. [PDF][source]
  • Philipp Altmann, Leonard Feuchtinger, Fabian Ritz, Jonas Nüßlein, Thomy Phan, and Claudia Linnhof-Popien, „CROP: Towards Distributional-Shift Robust Reinforcement Learning using Compact Reshaped Observation Processing“, in 32nd International Joint Conference on Artificial Intelligence (IJCAI ’23), 2023, to appear.
  • Thomy Phan, Fabian Ritz, Jonas Nüßlein, Michael Kölle, Thomas Gabor, and Claudia Linnhoff-Popien, „Attention-Based Recurrence for Multi-Agent Reinforcement Learning under State Uncertainty (Extended Abstract)“, in 22nd Conference on Autonomous Agents and Multiagent Systems (AAMAS ’23), 2023, to appear. [extended preprint][source]
  • Felip Guimerà Cuevas, Thomy Phan, Helmut Schmid, „Adaptive Bi-Nonlinear Neural Networks Based on Complex Numbers with Weights Constrained along the Unit Circle“, in 26th Pacific-Asia Conference on Knowledge Discovery and Data Mining (PAKDD ’23), 2023. [PDF]
  • Thomy Phan, Felix Sommer, Philipp Altmann, Fabian Ritz, Lenz Belzner, and Claudia Linnhoff-Popien, „Emergent Cooperation from Mutual Acknowledgment Exchange“, in 21st Conference on Autonomous Agents and Multiagent Systems (AAMAS ’22), 2022, pp. 1047–1055. [PDF][source][highlight paper]
  • Robert Müller, Steffen Illium, Thomy Phan, Tom Haider, and Claudia Linnhoff-Popien, „Towards Anomaly Detection in Reinforcement Learning“, in 21st Conference on Autonomous Agents and Multiagent Systems (AAMAS ’22 Blue Sky Ideas), 2022, pp. 1799–1803. [PDF]
  • Thomy Phan, Fabian Ritz, Lenz Belzner, Philipp Altmann, Thomas Gabor, and Claudia Linnhoff-Popien, „VAST: Value Function Factorization with Variable Agent Sub-Teams“, in 35th Conference on Neural Information Processing Systems (NeurIPS ’21), 2021, pp. 24018-24032. [PDF][source]
  • Thomy Phan, Lenz Belzner, Thomas Gabor, Andreas Sedlmeier, Fabian Ritz, and Claudia Linnhoff-Popien, „Resilient Multi-Agent Reinforcement Learning with Adversarial Value Decomposition“, in 35th AAAI Conference on Artificial Intelligence (AAAI ’21), 2021, pp. 11308–11316. [PDF][source]
  • Fabian Ritz, Daniel Ratke, Thomy Phan, Lenz Belzner, and Claudia Linnhoff-Popien, „A Sustainable Ecosystem through Emergent Cooperation in Multi-Agent Reinforcement Learning“, in Conference on Artificial Life (ALIFE ’21), 2021. [PDF][source]
  • Thomas Gabor, Thomy Phan, and Claudia Linnhoff-Popien, „Productive Fitness in Diversity-Aware Evolutionary Algorithms“, in Natural Computing (NACO ’21), 2021. [PDF]
  • Fabian Ritz, Felix Hohnstein, Robert Müller, Thomy Phan, Thomas Gabor, Claudia Linnhoff-Popien, and Carsten Hahn, „Towards Ecosystem Management from Greedy Reinforcement Learning in a Predator-Prey Setting“, in Conference on Artificial Life (ALIFE ’20), 2020, pp. 518-525. [PDF]
  • Carsten Hahn, Fabian Ritz, Paula Wikidal, Thomy Phan, Thomas Gabor, and Claudia Linnhoff-Popien, „Foraging Swarms using Multi-Agent Reinforcement Learning“, in Conference on Artificial Life (ALIFE ’20), 2020, pp. 333–340. [PDF]
  • Thomy Phan, Thomas Gabor, Andreas Sedlmeier, Fabian Ritz, Bernhard Kempter, Cornel Klein, Horst Sauer, Reiner Schmid, Jan Wieghardt, Marc Zeller, and Claudia Linnhoff-Popien, „Learning and Testing Resilience in Cooperative Multi-Agent Systems“, in 19th Conference on Autonomous Agents and Multiagent Systems (AAMAS ’20), 2020, pp. 1055-1063. [PDF][video]
  • Thomy Phan, Lenz Belzner, Kyrill Schmid, Thomas Gabor, Fabian Ritz, Sebastian Feld, and Claudia Linnhoff-Popien, „A Distributed Policy Iteration Scheme for Cooperative Multi-Agent Policy Approximation“, in Adaptive and Learning Agents Workshop (ALA@AAMAS ’20), 2020. [PDF][video]
  • Christoph Roch, Thomy Phan, Sebastian Feld, Robert Müller, Thomas Gabor, Carsten Hahn, and Claudia Linnhoff-Popien, „A Quantum Annealing Algorithm for Finding Pure Nash Equilibria in Graphical Games“, in 20th International Conference on Computational Science (ICCS ’20), 2020. [PDF]
  • Thomas Gabor, Andreas Sedlmeier, Thomy Phan, Fabian Ritz, Marie Kiermeier, Lenz Belzner, Bernhard Kempter, Cornel Klein, Horst Sauer, Reiner Schmid, Jan Wieghardt, Marc Zeller, and Claudia Linnhoff-Popien, „The Scenario Coevolution Paradigm: Adaptive Quality Assurance for Adaptive Systems“, in International Journal on Software Tools for Technology Transfer (STTT ’20), 2020, pp. 457-476. [PDF]
  • Thomy Phan, Thomas Gabor, Robert Müller, Christoph Roch, and Claudia Linnhoff-Popien, „Adaptive Thompson Sampling Stacks for Memory Bounded Open-Loop Planning“, in 28th International Joint Conference on Artificial Intelligence (IJCAI ’19), 2019, pp. 5607-5613. [PDF][source]
  • Thomas Gabor, Jan Peter, Thomy Phan, Christian Meyer, and Claudia Linnhoff-Popien, „Subgoal-Based Temporal Abstraction in Monte-Carlo Tree Search“, in 28th International Joint Conference on Artificial Intelligence (IJCAI ’19), 2019, pp. 5562-5568. [PDF][source]
  • Carsten Hahn, Thomy Phan, Thomas Gabor, Lenz Belzner, and Claudia Linnhoff-Popien, „Emergent Escape-based Flocking Behavior using Multi-Agent Reinforcement Learning“, in Conference on Artificial Life (ALIFE ’19), 2019, pp. 598–605. [PDF]
  • Thomas Gabor, Andreas Sedlmeier, Marie Kiermeier, Thomy Phan, Marcel Henrich, Monika Picklmair, Bernhard Kempter, Cornel Klein, Horst Sauer, Reiner Schmid, and Jan Wieghardt, „Scenario Co-Evolution for Reinforcement Learning on a GridWorld Smart Factory Domain“, in 28th Genetic and Evolutionary Computation Conference (GECCO ’19), 2019, pp. 898-906. [PDF]
  • Thomy Phan, Kyrill Schmid, Lenz Belzner, Thomas Gabor, Sebastian Feld, and Claudia Linnhoff-Popien, „Distributed Policy Iteration for Scalable Approximation of Cooperative Multi-Agent Policies (Extended Abstract)“, in 18th Conference on Autonomous Agents and Multiagent Systems (AAMAS ’19), 2019, pp. 2162-2164. [PDF][extended preprint]
  • Thomy Phan, Lenz Belzner, Marie Kiermeier, Markus Friedrich, Kyrill Schmid, and Claudia Linnhoff-Popien, „Memory Bounded Open-Loop Planning in Large POMDPs using Thompson Sampling“, in 33rd AAAI Conference on Artificial Intelligence (AAAI ’19), 2019, pp. 7941-7948. [PDF][source]
  • Thomy Phan, Lenz Belzner, Thomas Gabor, and Kyrill Schmid, „Leveraging Statistical Multi-Agent Online Planning with Emergent Value Function Approximation“, in 17th Conference on Autonomous Agents and Multiagent Systems (AAMAS ’18), 2018, pp. 730-738. [PDF]
  • Fang Huang*, George Sirinakis*, Edward S. Allgeyer, Lena K. Schroeder, Whitney C. Duim, Emil B. Kromann, Thomy Phan, Felix E. Rivera-Molina, Jordan R. Myers, Irnov Irnov, Mark Lessard, Yongdeng Zhang, Mary Ann Handel, Christine Jacobs-Wagner, C. Patrick Lusk, James E. Rothman, Derek Toomre, Martin J. Booth, Joerg Bewersdorf, „Ultra-High Resolution 3D Imaging of Whole Cells“, in Cell 166, 2016, pp. 1028-1040. *equal authorship [PDF]

Supervised Theses

Master Theses

  • Katharina Winter, Philipp Altmann, Thomy Phan, „Consensus-Based Mutual Acknowledgment Token Exchange“, 2023, ongoing
  • Balthasar Schüss, Thomy Phan, Michael Kölle, „Generalizing Agents in the Starcraft Multi-Agent Challenge“, 2023
  • Alain Feimer, Thomy Phan, Philipp Altmann, „Generalization in Multi-Agent Reinforcement Learning using Minimax Learning“, 2023
  • Alexander Perzl, Thomy Phan, Fabian Ritz, “ A Spatial Social Dilemma Environment for Multi-Agent Reinforcement Learning“, 2023
  • Arnold Unterauer, Thomy Phan, Philipp Altmann, „Hidden Attacks in Multi-Agent Reinforcement Learning“, 2023
  • Nicolas Kraus, Christoph Roch, Thomy Phan, „Classification of Classical and Quantum Algorithms with Artificial Neural Networks“, 2022
  • Hasan Turalic, Robert Müller, Thomy Phan, „Decentralized Multi-Agent Communication by Transmitting Cluster Indices“, 2022
  • Liliane Kabboura, Thomas Gabor, Thomy Phan, „Reward Shaping for Optimal Exploration in Reinforcement Learning“, 2022
  • Nina Czogalla, Thomy Phan, Fabian Ritz, „Adaptive Resilient Multi-Agent Reinforcement Learning“, 2022
  • Felix Sommer, Thomy Phan, Philipp Altmann, „Learning Trust in Multi-Agent Systems“, 2021. [paper]
  • Korbinian Blanz, Thomy Phan, Thomas Gabor, „Evaluating Resilience in Antagonist-based Multi-Agent Reinforcement Learning“, 2021
  • Manuel Zierl, Carsten Hahn, Thomy Phan, Fabian Ritz, „Analysis and Improvement of Communication in Cooperative Reinforcement Learning“, 2021
  • Jonas Nüßlein, Thomas Gabor, Thomy Phan, „Reinforcement Learning for Arbitrary Target Observations“, 2021
  • Simon Cronjaeger, Thomy Phan, Thomas Gabor, „Neural Architecture Search using Upside Down Reinforcement Learning“, 2021
  • Maximilian Wagner, Thomas Gabor, Thomy Phan, „An Evolutionary Algorithm for API Design Optimization in Software Ecosystems“, 2021
  • Patrick Börzel, Thomas Gabor, Thomy Phan, „Randomized Fitness in Evolutionary Algorithms“, 2020
  • Philipp Altmann, Thomas Gabor, Thomy Phan, „Adversarial Self-Imitation Learning“, 2020
  • Felip Guimera Cuevas, Thomy Phan, Thomas Gabor, „Uncorrelated and Prioritized Reservoir Sampling for Reinforcement Learning with Restricted Memory over Arbitrary Time-Spans“, 2020
  • Daniel Hämmerle, Andreas Sedlmeier, Thomy Phan, „Uncertainty-based Selection of DQN Agents“, 2020
  • Hila Safi, Thomas Gabor, Thomy Phan, „Analyzing Quadratic Unconstrained Binary Optimization (QUBO) Matrices using Neural Networks for Solving NP-complete Problems“, 2020. [paper]
  • Max Peters, Thomy Phan, Fabian Ritz, „Assembly of Multi-Agent Formations using Reinforcement Learning“, 2020
  • Andreas Mayer, Sebastian Feld, Thomy Phan, „Competitive Spatio-Temporal Search with Mobile Agents“, 2019
  • David Gehring, Thomy Phan, Steffen Illium, „Reinforcement Learning with Graph-Convolutional Neural Networks“, 2018
  • Christian Ungnadner, Kyrill Schmid, Thomy Phan, „Deep Experience Planner“, 2018
  • Jan Peter, Thomas Gabor, Thomy Phan, „Subgoal-Based Temporal Abstractions in Monte-Carlo Tree Search“, 2018. [paper]
  • Judith Mosandl, Kyrill Schmid, Thomy Phan, „Application of Hybrid Reward Functions for Complexity Reduction in Technical Real-World Domains“, 2018

Bachelor Theses

  • Felix Topp, Michael Kölle, Thomy Phan, „Quantum Multi-Agent Reinforcement Learning using Evolutionary Optimization“, 2023, ongoing
  • Julian Schönberger, Thomas Gabor, Thomy Phan, „Genetic Neuron Selection for Deep Neural Networks“, 2023, ongoing
  • Carlos Göhring, Thomy Phan, Kyrill Schmid, „Finding Dominant Strategies and Equilibria in Minority Games Using Reinforcement Learning“, 2022
  • Paul Seipl, Thomy Phan, Fabian Ritz, „Evaluation of Aggregation Mechanisms for Federated Reinforcement Learning“, 2022
  • Weronika Maniszewska, Thomy Phan, Fabian Ritz, „Multi-Agent Reinforcement Learning with Transformer-Based Policies“, 2022
  • Marco Börner, Thomy Phan, Philipp Altmann, „Predicting the Optimal Approximation Level for Quantum Annealing“, 2022
  • Hyeri An, Thomy Phan, Thomas Gabor, „Evolutionary Subgoal-Discovery for Temporal Abstract Planning“, 2022
  • Florian Grzonka, Thomas Gabor, Thomy Phan, „Predicting Hyperparameters for Evolutionary Algorithms using Neural Networks“, 2022
  • Tim Hesse, Thomas Gabor, Thomy Phan, „Reinforcement Learning for Imperfect Information Games Using the Trick Card Game Schafkopf as a Case Study“, 2021
  • Caroline Reinig, Thomy Phan, Fabian Ritz, „Pretraining of Reinforcement Learning Models for Federated Learning“, 2021
  • David Müller, Thomas Gabor, Thomy Phan, „Representing Algorithmic Properties of Learning Algorithms within their Reward Function“, 2021
  • Louis Mackenzie-Smith, Fabian Ritz, Thomy Phan, „Creation of a Standard Challenge Dataset for Scalable Supervision in Reinforcement Learning“, 2021
  • Christian Reff, Fabian Ritz, Thomy Phan, „Adapting MCTS Planning Algorithms to a Continuous Domain“, 2021
  • Marian Lingsch, Thomas Gabor, Thomy Phan, „AI for Programming: Prediction of Code Snippets from UML“, 2021
  • David Hansmair, Thomy Phan, Fabian Ritz, „Hexar.io as a Challenging Benchmark for Multi-Agent Reinforcement Learning“, 2020
  • Miriam Fischer, Thomy Phan, Robert Müller, Steffen Illium, „Stackelberg Routing with Fairness Considerations“, 2020
  • Antonia Halbig, Thomas Gabor, Thomy Phan, „Reinforcement Learning Targeting Arbitrary Expected Rewards“, 2020
  • Marc Leichsenring, Thomas Gabor, Thomy Phan, „Multi-headed Modification to the Monte Carlo Tree Search with Variable Search Depth“, 2020
  • Marco Philip, Thomy Phan, Thomas Gabor, „Adversarial Planning for Pursuit-Evasion Scenarios“, 2020
  • Patricia Gschoßmann, Thomy Phan, Thomas Gabor, „Learning to Play Pommerman with Emergent Communication“, 2020
  • Adam Mahmoud, Thomas Gabor, Thomy Phan, „Explainability of a Reinforcement Learning Agent for Autonomous Driving“, 2020
  • Elena Terzieva, Thomy Phan, Robert Müller, „Multi-Step Deep Q-Networks with Stacked Target Networks“, 2019
  • Sonja Geffert, Thomy Phan, Fabian Ritz, „Pooling of Target Networks in Deep Reinforcement Learning“, 2019

Project Work

  • Daniel Ratke, Fabian Ritz, Thomy Phan, „A Sustainable Ecosystem through Emergent Cooperation in Multi-Agent Reinforcement Learning“, 2021. [paper]
  • Felip Guimera Cuevas, Thomy Phan, Thomas Gabor, „Complex Value-based Deep Learning and Applications to Reinforcement Learning“, 2021. [paper]
  • Daniel Ratke, Thomy Phan, Fabian Ritz, „GRAB Zero“, 2020
  • Simon Cronjaeger, Thomy Phan, Robert Müller, „Development of a Predator-Prey Domain for Multi-Agent Reinforcement Learning“, 2020
  • Jonas Nüßlein, Thomas Gabor, Thomy Phan, „Upside-Down Reinforcement Learning and Related Approaches“, 2020
  • Korbinian Blanz, Thomy Phan, Thomas Gabor, „Implementation of a Testbed for Adversarial Multi-Agent Reinforcement Learning“, 2020
  • Michael Kessler, Thomy Phan, Thomas Gabor, „Enhancing Value-based Reinforcement Learning with Tree Search“, 2020
  • Johannes Handloser, Kyrill Schmid, Thomy Phan, „Implementation of a Test Environment for Multi-Agent Reinforcement Learning Algorithms“, 2018

on Google Scholar, ResearchGate, and LinkedIn