Selected Publications

* indicates co-first authorship; α–β order indicates alphabetical author ordering

2026

Limitations of Synthetic Data Generation in Specialized Data-Scarce Domains

Edward Zhang, Marcel Hussing, Tanay Tandon, Shenbagaraj Kannapiran, Jason Hughes, Youkang Wang, Joshua Caswell, Agelos Kratimenos, Yi Fan Li, Milan Manoj, Ethan Sanchez, Sumukh Shrote, Camillo Jose Taylor, Daniel A. Hashimoto, Eric Eaton
arXiv Preprint, 2026

Model Agreement via Anchoring

Eric Eaton, Surbhi Goel, Marcel Hussing, Michael Kearns, Aaron Roth, Sikata Bela Sengupta, Jessica Sorrell
Conference on Learning Theory, 2026

Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure

Max Lamparth, Daniel Fein, Andreas Haupt, Marcel Hussing, Mykel J. Kochenderfer
arXiv Preprint, 2026

Behavior-Consistent Deep Reinforcement Learning

Marcel Hussing*, Liv G. d'Aliberti*, Claas Voelcker, Benjamin Eysenbach, Eric Eaton
arXiv Preprint, 2026

Iterative Compositional Data Generation for Robot Control

Anh-Quan Pham, Marcel Hussing, Shubhankar P. Patankar, Dani S. Bassett, Jorge Mendez-Mendez, Eric Eaton
Transactions on Machine Learning Research, 2026

Replicable Reinforcement Learning with Linear Function Approximation

(α–β) Eric Eaton, Marcel Hussing, Michael Kearns, Aaron Roth, Sikata Bela Sengupta, Jessica Sorrell
International Conference on Learning Representations, 2026

Relative Entropy Pathwise Policy Optimization

Claas Voelcker, Axel Brunnbauer, Marcel Hussing, Michal Nauman, Pieter Abbeel, Eric Eaton, Radu Grosu, Amir-massoud Farahmand, Igor Gilitschenski
International Conference on Learning Representations, 2026

2025

Intersectional Fairness in Reinforcement Learning with Large State and Constraint Spaces

(α–β) Eric Eaton, Marcel Hussing, Michael Kearns, Aaron Roth, Sikata Bela Sengupta, Jessica Sorrell
International Conference on Machine Learning, 2025

Mad-td: Model-augmented data stabilizes high update ratio rl

Claas A Voelcker*, Marcel Hussing*, Eric Eaton, Amir-massoud Farahmand, Igor Gilitschenski
International Conference on Learning Representations (Spotlight), 2025

Future Slot Prediction for Unsupervised Object Discovery in Surgical Video

G Liao, M Jogan, M Hussing, E Zhang, E Eaton, DA Hashimoto
International Conference on Medical Image Computing and Computer Assisted Intervention, 2025

2024

Oracle-Efficient Reinforcement Learning for Max Value Ensembles

(α–β) Marcel Hussing, Michael Kearns, Aaron Roth, Sikata Bela Sengupta, Jessica Sorrell
Conference on Neural Information Processing Systems, 2024

Dissecting Deep RL with High Update Ratios: Combatting Value Divergence

Marcel Hussing*, Claas A Voelcker*, Amir Massoud Farahmand, Igor Gilitschenski, Eric Eaton
Reinforcement Learning Conference, 2024

Robotic Manipulation Datasets for Offline Compositional Reinforcement Learning

Marcel Hussing*, Jorge A. Mendez*, Anisha Singrodia, Cassandra Kent, Eric Eaton
Reinforcement Learning Conference, 2024

2023

Replicable Reinforcement Learning

(α–β) Eric Eaton, Marcel Hussing, Michael Kearns, Jessica Sorrell
Conference on Neural Information Processing Systems, 2023

2022

CompoSuite: A Compositional Reinforcement Learning Benchmark

Jorge A. Mendez*, Marcel Hussing*, Meghna Gummadi, Eric Eaton
Conference on Lifelong Learning Agents, 2022

2020

Structured Object-Aware Physics Prediction for Video Modeling and Planning

Jannik Kossen*, Karl Stelzner*, Marcel Hussing, Claas A. Voelcker, Kristian Kersting
International Conference on Learning Representations, 2020