Hasso-Plattner-Institut
Prof. Dr. h.c. mult. Hasso Plattner
 

Alexander Kastius

Research Assistant, PhD Candidate

Phone:    +49 (331) 5509-560
Fax:    +49 (331) 5509-579
Email:    alexander.kastius(at)hpi.de
Room:    V-2.05 (Campus II)
LinkedIn: Profile

Research

Reinforcement Learning for Revenue Management

My Research field is Reinforcement Learning for Revenue Management
I investigate improvements regarding stability and data efficiency of reinforcement learning algorithms when used on economic problems
in order to allow the practical application of those tools even when strong constraints regarding the available information have to be considered.

A detailed description of my research projects is available here.

Teaching

  • Dynamic Programming and Reinforcement Learning, Lecture - Summer Semester 2021
  • Online Marketplace Simulation: A Testbed for Self-Learning Agents, Bachelors Project - Starting Winter Semester 2021

Selected Talks

  • Dynamic Pricing under Competition using Reinforcement Learning, Euro 2021 Athens
  • Upcoming talk: Towards Transfer Learning for Revenue and Pricing Management, OR Conference Bern 2021, GOR e.V.
  • Talks in cooperation with the HPI research schools, including their weekly presentations and at the University of California, Irvine

Publications

2023

  • 1.
    Schröder, K., Kastius, A., Schlosser, R.: A Comparison of State-of-the-Art Reinforcement Learning Algorithms Applied to the Traveling Salesman Problem. The Knowledge Engineering Review, accepted. (2023).
     
  • 2.
    Groeneveld, J., Herrmann, J., Mollenhauer, N., Dreessen, L., Bessin, N., Schulze-Tast, J., Kastius, A., Huegle, J., Schlosser, R.: Self-Learning Agents for Recommerce Markets. Business & Information Systems Engineering, accepted. (2023).
     
  • 3.
    Schröder, K., Kastius, A., Schlosser, R.: Welcome to the Jungle: A Conceptual Comparison of Reinforcement Learning Algorithms. ICORES 2023. pp. 143–150 (2023).
     

2022

  • 1.
    Kastius, A., Schlosser, R.: Multi-Agent Dynamic Pricing Using Reinforcement Learning and Asymmetric Information. Operations Research Proceedings (OR2022), to appear (2022).
     
  • 2.
    Schlosser, R., Kastius, A.: A Conceptual Framework for Studying Self-Learning Agents in Recommerce Markets. Operations Research Proceedings (OR 2022), to appear (2022).
     
  • 3.
    Kossmann, J., Kastius, A., Schlosser, R.: SWIRL: Selection of Workload-aware Indexes using Reinforcement Learning. 25th International Conference on Extending Database Technology (EDBT 2022). pp. 155–168 (2022).
     
  • 4.
    Schlosser, R., Kastius, A.: Stochastic Dynamic Pricing under Duopoly Competition with Mutual Strategy Adjustments. Operations Research Proceedings (OR 2021). pp. 367–372 (2022).
     
  • 5.
    Kastius, A., Schlosser, R.: Towards Transfer Learning for Revenue and Pricing Management. Operations Research Proceedings, OR2021. pp. 361–366 (2022).
     
  • 6.
    Kastius, A., Schlosser, R.: Dynamic Pricing under Competition using Reinforcement Learning. Journal of Revenue and Pricing Management. 21, 50–63 (2022).