InstitutTeam
Aditya Mohan

Aditya Mohan, M. Sc.

Aditya Mohan, M. Sc.
Adresse
Appelstraße 9a
30167 Hannover
Gebäude
Raum
Aditya Mohan, M. Sc.
Adresse
Appelstraße 9a
30167 Hannover
Gebäude
Raum

I am working towards my Ph.D. at the intersection of Reinforcement Learning, Meta-Learning, and AutoML as a doctoral researcher at Leibniz University since October 2021. Previously, I attained my Master's degree from Technische Universität Berlin and EURECOM where my thesis focused on using Meta-Learning and Reinforcement Learning to train an agent to adapt to the playing styles of diverse partners in the game of Hanabi, under the supervision of Dr. Klaus Obermayer.

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. Hence, I am interested in applying RL to domain adaptation, zero-shot policy transfer, e.t.c.

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 in Reinforcement Learning
  • Dynamic Algorithm Configuration
  • Automated Reinforcement Learning
  • Meta Reinforcement Learning
  • Multi-fidelity Information Fusion for Reinforcement Learning

Curriculum Vitae

  • Education

    October, 2021 - Present: Doctoral Researcher 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

Publications

  • Aditya Mohan, Tim Ruhkopf, Marius Lindauer (2022): Towards Meta-learned Algorithm Selection using Implicit Fidelity InformationICML Workshop on Adaptive Experimental Design and Active Learning in the Real World (ReALML)
    arXiv: 2206.03130
  • Carolin Benjamins, Theresa Eimer, Frederik Schubert, Aditya Mohan, André Biedenkapp, Bodo Rosenhahn, Frank Hutter, Marius Lindauer (2022): Contextualize Me - The Case for Context in Reinforcement LearningArXiv Preprint
    arXiv: https://arxiv.org/abs/2202.04500

Projects

  • Dynamic Algorithm Configuration
    Da die Konfigurationen während der Laufzeit in Abhängigkeit vom aktuellen Zustand des Algorithmus ausgewählt werden sollten, kann es als ein Problem des Reinforcement Learning (RL) betrachtet werden, bei dem ein Agent in jedem Zeitschritt die zu verwendende Konfiguration auf der Grundlage der Leistung im letzten Schritt und des aktuellen Zustands des Algorithmus auswählt. Dies ermöglicht uns einerseits den Einsatz leistungsfähiger RL-Methoden, andererseits bringt RL auch eine Reihe von Herausforderungen mit sich, wie Instabilität, Rauschen und Ineffizienz bei der Abtastung, die bei Anwendungen wie DAC angegangen werden müssen. Daher umfasst die Forschung zu DAC auch die Forschung zu zuverlässigem, interpretierbarem, allgemeinem und schnellem Reinforcement Learning.
    Leitung: Prof. Dr. Marius Lindauer
    Jahr: 2019
    Förderung: DFG
    Laufzeit: 2019-2023
  • Dynamic Algorithm Configuration
    As configurations should be chosen during runtime depending on the current algorithm state, it can be viewed as a reinforcement learning (RL) problem where at each timestep an agent selects the configuration to use based on the performance in the last step and the current state of the algorithm. This enables us to use powerful RL methods on one hand; on the other, RL also brings a set of challenges like instability, noise and sample inefficiency that need to be addressed in applications such as DAC. Therefore research on DAC also includes research on reliable, interpretable, general and fast reinforcement learning.
    Leitung: Prof. Dr. Marius Lindauer
    Jahr: 2019
    Förderung: DFG
    Laufzeit: 2019-2023
  • Leibniz AI Academy
    The Leibniz AI Academy aims to develop and establish a trans-curricular and interdisciplinary micro-degree program at the Leibniz Universität Hannover (LUH), in which students from different courses of study acquire competencies in the field of Artificial Intelligence
    Leitung: Prof. Dr. Marius Lindauer, Prof. Dr. Ralph Ewert, Prof. Dr. Johannes Krugel
    Jahr: 2021
    Förderung: Bundesministerium für Bildung und Forschung (BMBF)
    Laufzeit: 2021 - 2024
    Logo of Leibniz AI academy Logo of Leibniz AI academy