Publications

Publications are listed in reversed chronological order.

2022

  1. DeepCAVE: An Interactive Analysis Tool for Automated Machine Learning
    René Sass, Eddie Bergman,  André BiedenkappFrank Hutter, and Marius Lindauer
    In Workshop on Adaptive Experimental Design and Active Learning in the Real World (ReALML@ICML’22) 2022
  2. Learning Domain-Independent Policies for Open List Selection
    André BiedenkappDavid Speck, Silvan Sievers, Frank HutterMarius Lindauer, and Jendrik Seipp
    In Workshop on Bridging the Gap Between AI Planning and Reinforcement Learning (PRL@ICAPS’22) 2022
  3. Theory-inspired Parameter Control Benchmarks for Dynamic Algorithm Configuration
    André Biedenkapp, Nguyen Dang, Martin S. Krejca, Frank Hutter, and Carola Doerr
    In Proceedings of the Genetic and Evolutionary Computation Conference (GECCO’22) 2022 Joint first authorship: André Biedenkapp & Nguyen Dang & Martin S. Krejca, Nominated for the best paper award
  4. Automated Reinforcement Learning (AutoRL): A Survey and Open Problems
    Jack Parker-Holder, Raghu Rajan, Xingyou Song,  André Biedenkapp, Yingjie Miao, Theresa Eimer, Baohe Zhang, Vu Nguyen, Roberto Calandra, Aleksandra Faust, Frank Hutter, and Marius Lindauer
    Journal of Artificial Intelligence Research (JAIR) 2022
  5. Automated Dynamic Algorithm Configuration
    Steven Adriaensen,  André Biedenkapp, Gresa Shala, Noor Awad, Theresa EimerMarius Lindauer, and Frank Hutter
    arXiv:2205.13881 [cs.AI] 2022
  6. Contextualize Me – The Case for Context in Reinforcement Learning
    Carolin BenjaminsTheresa Eimer, Frederik Schubert, Aditya Mohan,  André Biedenkapp, Bodo Rosenhan, Frank Hutter, and Marius Lindauer
    arXiv:2202.04500 2022
  7. SMAC3: A Versatile Bayesian Optimization Package for Hyperparameter Optimization
    Marius Lindauer, Katharina Eggensperger, Matthias Feurer,  André Biedenkapp, Difan Deng, Carolin Benjamins, Tim Ruhkopf, René Sass, and Frank Hutter
    Journal of Machine Learning Research (JMLR) – MLOSS 2022

2021

  1. CARL: A Benchmark for Contextual and Adaptive Reinforcement Learning
    Carolin BenjaminsTheresa Eimer, Frederik Schubert,  André Biedenkapp, Bodo Rosenhan, Frank Hutter, and Marius Lindauer
    In Workshop on Ecological Theory of Reinforcement Learning (EcoRL@NeurIPS’21) 2021
  2. DACBench: A Benchmark Library for Dynamic Algorithm Configuration
    Theresa EimerAndré Biedenkapp, Maximilian Reimer, Steven Adriaensen, Frank Hutter, and Marius Lindauer
    In Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI’21) 2021
  3. Learning Heuristic Selection with Dynamic Algorithm Configuration
    David SpeckAndré BiedenkappFrank Hutter, Robert Mattmüller, and Marius Lindauer
    In Proceedings of the Thirty-First International Conference on Automated Planning and Scheduling (ICAPS 2021) 2021 Joint first authorship: David Speck & André Biedenkapp
  4. TempoRL: Learning When to Act
    André Biedenkapp, Raghu Rajan, Frank Hutter, and Marius Lindauer
    In Proceedings of the 38th International Conference on Machine Learning (ICML 2021) 2021
  5. Self-Paced Context Evaluations for Contextual Reinforcement Learning
    Theresa EimerAndré BiedenkappFrank Hutter, and Marius Lindauer
    In Proceedings of the 38th International Conference on Machine Learning (ICML 2021) 2021
  6. Bag of Baselines for Multi-objective Joint Neural Architecture Search and Hyperparameter Optimization
    Sergio Izquierdo, Julia Guerrero-Viu, Sven Hauns, Guilherme Miotto, Simon Schrodi,  André Biedenkapp, Thomas Elsken, Difan Deng, Marius Lindauer, and Frank Hutter
    In Workshop on Automated Machine Learning (AutoML@ICML’21) 2021
  7. MDP Playground: A Design and Debug Testbed for Reinforcement Learning
    Raghu Rajan, Jessica Lizeth Borja Diaz, Suresh Guttikonda, Fabio Ferreira,  André Biedenkapp, Jan Ole Hartz, and Frank Hutter
    arXiv:1909.07750 [cs.LG] 2021
  8. Sample-Efficient Automated Deep Reinforcement Learning
    Jörg K H Franke, Gregor Köhler,  André Biedenkapp, and Frank Hutter
    International Conference on Learning Representations (ICLR) 2021 2021
  9. On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning
    Baohe Zhang, Raghu Rajan, Luis Pineda, Nathan Lambert,  André Biedenkapp, Kurtland Chua, Frank Hutter, and Roberto Calandra
    In Proceedings of the 24th International Conference on Artificial Intelligence and Statistics (AISTATS)’21 2021
  10. In-Loop Meta-Learning with Gradient-Alignment Reward
    Samuel Müller,  André Biedenkapp, and Frank Hutter
    In AAAI workshop on Meta-Learning Challenges 2021

2020

  1. Squirrel: A Switching Hyperparameter Optimizer Description of the entry by AutoML.org & IOHprofiler to the NeurIPS 2020 BBO challenge
    Noor Awad, Gresa Shala, Difan Deng, Neeratyoy Mallik, Matthias Feurer, Katharina Eggensperger,  André Biedenkapp, Diederick Vermetten, Hao Wang, Carola DoerrMarius Lindauer, and Frank Hutter
    arXiv:2012.08180 [cs.LG] 2020 Winner of the NeurIPS 2020 BBO challenge on the meta-learning friendly track
  2. Learning Heuristic Selection with Dynamic Algorithm Configuration
    David SpeckAndré BiedenkappFrank Hutter, Robert Mattmüller, and Marius Lindauer
    In ICAPS 2020 Workshop on Bridging the Gap Between AI Planning and Reinforcement Learning (PRL) 2020 Joint first authorship: David Speck & André Biedenkapp
  3. Learning Step-Size Adaptation in CMA-ES
    Gresa Shala,  André Biedenkapp, Noor Awad, Steven Adriaensen, Marius Lindauer, and Frank Hutter
    In Proceedings of the Sixteenth International Conference on Parallel Problem Solving from Nature (PPSN’20) 2020 Joint first authorship: Gresa Shala & André Biedenkapp
  4. Towards TempoRL: Learning When to Act
    André Biedenkapp, Raghu Rajan, Frank Hutter, and Marius Lindauer
    In Workshop on Inductive Biases, Invariances and Generalization in RL (BIG@ICML’20) 2020
  5. Towards Self-Paced Context Evaluations for Contextual Reinforcement Learning
    Theresa EimerAndré BiedenkappFrank Hutter, and Marius Lindauer
    In Workshop on Inductive Biases, Invariances and Generalization in RL (BIG@ICML’20) 2020
  6. Dynamic Algorithm Configuration: Foundation of a New Meta-Algorithmic Framework
    André Biedenkapp, Furkan H Bozkurt, Theresa EimerFrank Hutter, and Marius Lindauer
    In Proceedings of the Twenty-fourth European Conference on Artificial Intelligence (ECAI’20) 2020

2019

  1. Towards White-box Benchmarks for Algorithm Control
    André Biedenkapp, Furkan H. Bozkurt, Frank Hutter, and Marius Lindauer
    In IJCAI 2019 DSO Workshop 2019
  2. BOAH: A Tool Suite for Multi-Fidelity Bayesian Optimization & Analysis of Hyperparameters
    Marius Lindauer, Katharina Eggensperger, Matthias Feurer,  André Biedenkapp, Joshua Marben, Philipp Müller, and Frank Hutter
    arXiv:1908.06756 [cs.LG] 2019
  3. Towards Assessing the Impact of Bayesian Optimization’s Own Hyperparameters
    Marius Lindauer, Matthias Feurer, Katharina Eggensperger,  André Biedenkapp, and Frank Hutter
    In IJCAI 2019 DSO Workshop 2019

2018

  1. CAVE: Configuration Assessment, Visualization and Evaluation
    André Biedenkapp, Joshua Marben, Marius Lindauer, and Frank Hutter
    In Proceedings of the International Conference on Learning and Intelligent Optimization (LION’18) 2018

2017

  1. Efficient Parameter Importance Analysis via Ablation with Surrogates
    André BiedenkappMarius Lindauer, Katharina Eggensperger, Chris Fawcett, Holger H Hoos, and Frank Hutter
    In Proceedings of the Thirty-First Conference on Artificial Intelligence (AAAI’17) 2017