Aditya Mohan
Adresse
Welfengarten 1
30167 Hannover
Gebäude
Raum
Aditya Mohan
Adresse
Welfengarten 1
30167 Hannover
Gebäude
Raum

I am interested in developing generalizable and deployable Reinforcement Learning pipelines that can abstract useful structures from multiple kinds of environments, and then use these structures for prediction, planning, and learning. To this end, I believe techniques from the field of AutoML can help scale sequential decision-making techniques like Reinforcement Learning, and thus allow them to move beyond games and simulators to solving real-world problems like targeted medicine, resource optimization, etc. My long-term goal is to develop autonomous agents that can operate in sparse data regimes and integrate seamlessly into existing value chains fairly and equitably.

Research Interests

  • Generalization adn Deployability in Reinforcement Learning
  • Automated Reinforcement Learning
  • Meta Reinforcement Learning
  • Multi-fidelity Information Fusion for Reinforcement Learning

Curriculum Vitae

  • Work Experience

    October, 2021 - Present: Doctoral Researcher in the Automated Machine Learning group at Leibniz University of Hannover

    September, 2020 - December, 2020: Research Intern at Learning and Intelligent Systems Group at the Technical University of Berlin

    July, 2018 - September, 2019: Analyst in the Risk Consulting team in KPMG India

     

  • Education

    October, 2021 - Present: Ph.D. candidate at the Leibniz University Hannover

     

    2019 - 2021: M.Sc. in Autonomous Systems at the Teschnische Universität Berlin and EURECOM

    • Thesis: AI agents that quickly adapt to a partner for Ad.hoc cooperation in the game of Hanabi
    • Supervisor: Prof. Dr. Klaus Obermayer

     

    2014 - 2018: B.Tech in Electronics and Communication Engineering at Manipal Institute of Technology

Publications

Zeige Ergebnisse 1 - 11 von 11

2024


Benjamins C, Cenikj G, Nikolikj A, Mohan A, Eftimov T, Lindauer M. Instance Selection for Dynamic Algorithm Configuration with Reinforcement Learning: Improving Generalization. in Genetic and Evolutionary Computation Conference (GECCO). Association for Computing Machinery Special Interest Group on Genetic and Evolutionary Computation (SIGEVO). 2024
Mohan A, Zhang A, Lindauer M. Structure in Deep Reinforcement Learning: A Survey and Open Problems. Journal of Artificial Intelligence Research. 2024 Apr. Epub 2024 Apr.
Tornede A, Deng D, Eimer T, Giovanelli J, Mohan A, Ruhkopf T et al. AutoML in the Age of Large Language Models: Current Challenges, Future Opportunities and Risks. Transactions on Machine Learning Research. 2024 Feb 9. Epub 2024 Feb 9. doi: 10.48550/arXiv.2306.08107

2023


Benjamins C, Eimer T, Schubert FG, Mohan A, Döhler S, Biedenkapp A et al. Contextualize Me – The Case for Context in Reinforcement Learning. Transactions on Machine Learning Research. 2023 Jun 5;2023(6). Epub 2023 Jun 5. doi: 10.48550/arXiv.2202.04500
Benjamins C, Eimer T, Schubert FG, Mohan A, Döhler S, Biedenkapp A et al. Extended Abstract: Contextualize Me -- The Case for Context in Reinforcement Learning. in The 16th European Workshop on Reinforcement Learning (EWRL 2023). 2023 Epub 2023.
Loni M, Mohan A, Asadi M, Lindauer M. Learning Activation Functions for Sparse Neural Networks. in Second International Conference on Automated Machine Learning. PMLR. 2023
Mohan A, Zhang A, Lindauer M. A Patterns Framework for Incorporating Structure in Deep Reinforcement Learning. in The 16th European Workshop on Reinforcement Learning (EWRL 2023). 2023
Mohan A, Benjamins C, Wienecke K, Dockhorn A, Lindauer M. AutoRL Hyperparameter Landscapes. in Second International Conference on Automated Machine Learning. PMLR. 2023 Epub 2023 Jul 20. doi: 10.48550/arXiv.2304.02396
Mohan A, Benjamins C, Wienecke K, Dockhorn A, Lindauer M. Extended Abstract: AutoRL Hyperparameter Landscapes. in The 16th European Workshop on Reinforcement Learning (EWRL 2023). 2023
Ruhkopf T, Mohan A, Deng D, Tornede A, Hutter F, Lindauer M. MASIF: Meta-learned Algorithm Selection using Implicit Fidelity Information. Transactions on Machine Learning Research. 2023 Apr 18. Epub 2023 Apr 18.

2022


Mohan A, Ruhkopf T, Lindauer M. Towards Meta-learned Algorithm Selection using Implicit Fidelity Information. in ICML Workshop on Adaptive Experimental Design and Active Learning in the Real World (ReALML). 2022 Epub 2022 Jun 7.