| 2025 | ICLR | Accelerating Task Generalisation with Multi-Level Skill Hierarchies. | Thomas P. Cannon, zgr Simsek |
| 2025 | ICML | Position: Causal Machine Learning Requires Rigorous Synthetic Experiments for Broader Adoption. | Audrey Poinsot, Panayiotis Panayiotou, Alessandro Ferreira Leite, Nicolas Chesneau, zgr Simsek, Marc Schoenauer |
| 2024 | IROS | Identifying Optimal Launch Sites of High-Altitude Latex-Balloons using Bayesian Optimisation for the Task of Station-Keeping. | Jack Saunders, Sajad Saeedi G., Adam Hartshorne, Binbin Xu, zgr Simsek, Alan Hunter, Wenbin Li |
| 2023 | ICML | Explaining Reinforcement Learning with Shapley Values. | Daniel Beechey, Thomas M. S. Smith, zgr Simsek |
| 2023 | IROS | Resource-Constrained Station-Keeping for Latex Balloons Using Reinforcement Learning. | Jack Saunders, Loc Prenevost, zgr Simsek, Alan Hunter, Wenbin Li |
| 2021 | CHI | RL4HCI: Reinforcement Learning for Humans, Computers, and Interaction. | Dorota Glowacka, Andrew Howes, Jussi P. P. Jokinen, Antti Oulasvirta, zgr Simsek |
| 2019 | ICML | Regularization in directable environments with application to Tetris. | Jan Malte Lichtenberg, zgr Simsek |
| 2016 | ICML | Why Most Decisions Are Easy in Tetris - And Perhaps in Other Sequential Decision Problems, As Well. | zgr Simsek, Simn Algorta, Amit Kothiyal |
| 2009 | ICML | Workshop summary: Abstraction in reinforcement learning. | zgr Simsek |
| 2006 | ICML | An intrinsic reward mechanism for efficient exploration. | zgr Simsek, Andrew G. Barto |
| 2005 | AAAI | Towards Competence in Autonomous Agents. | zgr Simsek |
| 2005 | ICML | Identifying useful subgoals in reinforcement learning by local graph partitioning. | zgr Simsek, Alicia P. Wolfe, Andrew G. Barto |
| 2005 | IJCAI | Decentralized Search in Networks Using Homophily and Degree Disparity. | zgr Simsek, David D. Jensen |
| 2005 | KDD | Using relational knowledge discovery to prevent securities fraud. | Jennifer Neville, zgr Simsek, David D. Jensen, John Komoroske, Kelly Palmer, Henry G. Goldberg |
| 2004 | ICML | Using relative novelty to identify useful temporal abstractions in reinforcement learning. | zgr Simsek, Andrew G. Barto |