Scholar
Johannes Ackermann
Google Scholar ID: 2HvSMI8AAAAJ
The University of Tokyo
Citations & Impact
Citations
244
H-index
4
i10-index
2
Publications
8
Co-authors
11
list available
Publications
Resume (English only)
Academic Achievements
- Paper 'Off-Policy Corrected Reward Modeling for Reinforcement Learning from Human Feedback' accepted at COLM 2025
- Two papers accepted at RLC 2025: 'Recursive Reward Aggregation' and 'Offline Reinforcement Learning with Domain-Unlabeled Data'
- Paper 'Offline Reinforcement Learning from Datasets with Structured Non-Stationarity' accepted at RLC 2024
- Published 'Unsupervised Task Clustering for Multi-Task Reinforcement Learning' at ECML-PKDD 2021
- Contributed to multiple RL research directions including task representation, reward aggregation beyond discounted sum, and handling non-stationary datasets
