Johannes Ackermann

11 papers Journal 9Unranked 2
YearRankTypeTitle / Venue / Authors
2026 J jnl
Gradient Regularization Prevents Reward Hacking in Reinforcement Learning from Human Feedback and Verifiable Rewards.
CoRR
Johannes Ackermann, Michael Noukhovitch, Takashi Ishida, Masashi Sugiyama
2025 J jnl
Off-Policy Corrected Reward Modeling for Reinforcement Learning from Human Feedback.
CoRR
Johannes Ackermann, Takashi Ishida, Masashi Sugiyama
2025 J jnl
Recursive Reward Aggregation.
CoRR
Yuting Tang, Yivan Zhang, Johannes Ackermann, Yu-Jie Zhang, Soichiro Nishimori, Masashi Sugiyama
2024 J jnl
Leveraging Domain-Unlabeled Data in Offline Reinforcement Learning across Two Domains.
CoRR
Soichiro Nishimori, Xin-Qiang Cai, Johannes Ackermann, Masashi Sugiyama
2024 J jnl
Offline Reinforcement Learning from Datasets with Structured Non-Stationarity.
RLJ
Johannes Ackermann, Takayuki Osa, Masashi Sugiyama
2024 J jnl
Offline Reinforcement Learning from Datasets with Structured Non-Stationarity.
CoRR
Johannes Ackermann, Takayuki Osa, Masashi Sugiyama
2022 J jnl
High-Resolution Image Editing via Multi-Stage Blended Diffusion.
CoRR
Johannes Ackermann, Minjun Li
2021 — conf
Unsupervised Task Clustering for Multi-task Reinforcement Learning.
ECML/PKDD (1)
Johannes Ackermann, Oliver Richter, Roger Wattenhofer
2020 — conf
Convolutional Neural Network Based Blind Estimation of Generalized Mutual Information for Optical Communication.
ECOC
Johannes Ackermann, Maximilian Schädler, Christian Blümm
2020 J jnl
Impact of Acoustic and Interactive Disruptive Factors during Robot-Assisted Surgery - A Virtual Surgical Training Model.
Sensors
Magret Krüger, Johannes Ackermann, Daniar Osmonov, Veronika Günther, Dirk Bauerschlag, Johannes Hensler, Jan-Hendrik Egberts, Sebastian Lippross, Georgios Gitas, Thomas Becker, Nicolai Maass, Klaus-Peter Jünemann, Ibrahim Alkatout
2019 J jnl
Reducing Overestimation Bias in Multi-Agent Domains Using Double Centralized Critics.
CoRR
Johannes Ackermann, Volker Gabler, Takayuki Osa, Masashi Sugiyama