Research output per year
Research output per year
Personal profile
Research interests
I am interested in exploring how agents can learn to abstract structure out of tasks and use this to adapt better to different classes of tasks. Thus, I am currently working on gaining further insight into generalization and domain adaptation in Reinforcement Learning and Meta-Learning. My greater research ambition is to develop agents that can learn how to tune their own algorithms. My current research interests are:
- Contextual Reinforcement Learning
- Automated Reinforcement Learning
- Meta Reinforcement Learning
-
Mighty: A Comprehensive Tool for studying Generalization, Meta-RL and AutoRL
Mohan, A., Eimer, T., Benjamins, C., Lindauer, M. & Biedenkapp, A., Sept 2025, (E-pub ahead of print) 18th European Workshop on Reinforcement Learning (EWRL).Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
Open Access -
Moments Matter: Stabilizing Policy Optimization using Return Distributions
Jabs, D., Mohan, A. & Lindauer, M., 15 Feb 2025, (Accepted/In press) 2025 Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM 2025).Research output: Chapter in book/report/conference proceeding › Conference abstract › Research › peer review
-
ARLBench: Flexible and Efficient Benchmarking for Hyperparameter Optimization in Reinforcement Learning
Becktepe, J., Dierkes, J., Benjamins, C., Mohan, A., Salinas, D., Rajan, R., Hutter, F., Hoos, H., Lindauer, M. & Eimer, T., 2024, (E-pub ahead of print) 17th European Workshop on Reinforcement Learning (EWRL 2024).Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
-
AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Risks
Tornede, A., Deng, D., Eimer, T., Giovanelli, J., Mohan, A., Ruhkopf, T., Segel, S., Theodorakopoulos, D., Tornede, T., Wachsmuth, H. & Lindauer, M., 9 Feb 2024, (E-pub ahead of print) In: Transactions on Machine Learning Research.Research output: Contribution to journal › Article › Research › peer review
Open Access -
Instance Selection for Dynamic Algorithm Configuration with Reinforcement Learning: Improving Generalization
Benjamins, C., Cenikj, G., Nikolikj, A., Mohan, A., Eftimov, T. & Lindauer, M., 1 Aug 2024, Genetic and Evolutionary Computation Conference (GECCO). Association for Computing Machinery Special Interest Group on Genetic and Evolutionary Computation (SIGEVO), p. 563 - 566 4 p.Research output: Chapter in book/report/conference proceeding › Conference contribution › Research › peer review
Projects
- 2 Finished
-
LeibnizAI: Disziplinübergreifende, hybride Micro-Degrees für Studium und Weiterbildung
Ewerth, R. (Principal Investigator), Lindauer, M. T. (Principal Investigator), Krugel, J. A. (Principal Investigator), Sester, M. (Principal Investigator), Denkena, B. (Principal Investigator), Robak, S. (Principal Investigator), Abedjan, Z. (Principal Investigator), Wittich, E. K. (Principal Investigator), Weber, S. (Principal Investigator), Schanze, S. (Principal Investigator), Rottensteiner, F. (Principal Investigator), Auer, S. (Principal Investigator), Nejdl, W. (Principal Investigator), Feuerhake, U. (Principal Investigator) & Mohan, A. (Principal Investigator)
1 Dec 2021 → 30 Nov 2025
Project: Research
-
Algorithm Control: Efficient Learning to Control Algorithm Parameters
Lindauer, M. T. (Principal Investigator), Eimer-Rüegg, T. (Project staff), Benjamins, C. (Project staff) & Mohan, A. (Project staff)
1 Oct 2020 → 14 Sept 2024
Project: Research