Özgür Simsek

44 papers A* 12A 2Journal 20Unranked 10

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Causal Discovery in Action: Learning Chain-Reaction Mechanisms from Interventions. CoRR Panayiotis Panayiotou, Özgür Simsek
2025	J	`jnl`	A Theoretical Framework for Explaining Reinforcement Learning with Shapley Values. CoRR Daniel Beechey, Thomas M. S. Smith, Özgür Simsek
2025	A*	`conf`	Accelerating Task Generalisation with Multi-Level Skill Hierarchies. ICLR Thomas P. Cannon, Özgür Simsek
2025	J	`jnl`	Approximating Shapley Explanations in Reinforcement Learning. CoRR Daniel Beechey, Özgür Simsek
2025	J	`jnl`	CausalProfiler: Generating Synthetic Benchmarks for Rigorous and Transparent Evaluation of Causal Machine Learning. CoRR Panayiotis Panayiotou, Audrey Poinsot, Alessandro Ferreira Leite, Nicolas Chesneau, Marc Schoenauer, Özgür Simsek
2025	J	`jnl`	Learning The Minimum Action Distance. CoRR Lorenzo Steccanella, Joshua B. Evans, Özgür Simsek, Anders Jonsson
2025	—	`conf`	Position: Causal Machine Learning Requires Rigorous Synthetic Experiments for Broader Adoption. ICML (Position Papers) Audrey Poinsot, Panayiotis Panayiotou, Alessandro Ferreira Leite, Nicolas Chesneau, Özgür Simsek, Marc Schoenauer
2025	J	`jnl`	Position: Causal Machine Learning Requires Rigorous Synthetic Experiments for Broader Adoption. CoRR Audrey Poinsot, Panayiotis Panayiotou, Alessandro Ferreira Leite, Nicolas Chesneau, Özgür Simsek, Marc Schoenauer
2024	J	`jnl`	Accelerating Task Generalisation with Multi-Level Hierarchical Options. CoRR Thomas P. Cannon, Özgür Simsek
2024	J	`jnl`	Curricula for Learning Robust Policies with Factored State Representations in Changing Environments. CoRR Panayiotis Panayiotou, Özgür Simsek
2024	J	`jnl`	Hierarchical Orchestra of Policies. CoRR Thomas P. Cannon, Özgür Simsek
2024	A	`conf`	Identifying Optimal Launch Sites of High-Altitude Latex-Balloons using Bayesian Optimisation for the Task of Station-Keeping. IROS Jack Saunders, Sajad Saeedi G., Adam Hartshorne, Binbin Xu, Özgür Simsek, Alan Hunter, Wenbin Li
2024	J	`jnl`	Identifying Optimal Launch Sites of High-Altitude Latex-Balloons using Bayesian Optimisation for the Task of Station-Keeping. CoRR Jack Saunders, Sajad Saeedi, Adam Hartshorne, Binbin Xu, Özgür Simsek, Alan Hunter, Wenbin Li
2024	J	`jnl`	Interpretability in Action: Exploratory Analysis of VPT, a Minecraft Agent. CoRR Karolis Jucys, George Adamopoulos, Mehrab Hamidi, Stephanie Milani, Mohammad Reza Samsami, Artem Zholus, Sonia Joseph, Blake A. Richards, Irina Rish, Özgür Simsek
2024	J	`jnl`	Solving large-scale MEG/EEG source localisation and functional connectivity problems simultaneously using state-space models. NeuroImage Jose Miguel Sanchez Bornot, Roberto C. Sotero, J. A. Scott Kelso, Özgür Simsek, Damien Coyle
2023	J	`jnl`	Colour versus Shape Goal Misgeneralization in Reinforcement Learning: A Case Study. CoRR Karolis Ramanauskas, Özgür Simsek
2023	A*	`conf`	Creating Multi-Level Skill Hierarchies in Reinforcement Learning. NeurIPS Joshua B. Evans, Özgür Simsek
2023	J	`jnl`	Creating Multi-Level Skill Hierarchies in Reinforcement Learning. CoRR Joshua B. Evans, Özgür Simsek
2023	A*	`conf`	Explaining Reinforcement Learning with Shapley Values. ICML Daniel Beechey, Thomas M. S. Smith, Özgür Simsek
2023	J	`jnl`	Explaining Reinforcement Learning with Shapley Values. CoRR Daniel Beechey, Thomas M. S. Smith, Özgür Simsek
2023	J	`jnl`	Resource-Constrained Station-Keeping for Helium Balloons using Reinforcement Learning. CoRR Jack Saunders, Loïc Prenevost, Özgür Simsek, Alan Hunter, Wenbin Li
2023	A	`conf`	Resource-Constrained Station-Keeping for Latex Balloons Using Reinforcement Learning. IROS Jack Saunders, Loïc Prenevost, Özgür Simsek, Alan Hunter, Wenbin Li
2023	—	`conf`	The Temporal Persistence of Generative Language Models in Sentiment Analysis. CLEF (Working Notes) Pablo Medina-Alias, Özgür Simsek
2021	—	`conf`	RL4HCI: Reinforcement Learning for Humans, Computers, and Interaction. CHI Extended Abstracts Dorota Glowacka, Andrew Howes, Jussi P. P. Jokinen, Antti Oulasvirta, Özgür Simsek
2020	J	`jnl`	Fast and frugal heuristics for portfolio decisions with positive project interactions. Decis. Support Syst. Ian N. Durbach, Simón Algorta, Dieudonné Kabongo Kantu, Konstantinos V. Katsikopoulos, Özgür Simsek
2019	J	`jnl`	Iterative Policy-Space Expansion in Reinforcement Learning. CoRR Jan Malte Lichtenberg, Özgür Simsek
2019	A*	`conf`	Regularization in directable environments with application to Tetris. ICML Jan Malte Lichtenberg, Özgür Simsek
2019	J	`jnl`	The Game of Tetris in Machine Learning. CoRR Simón Algorta, Özgür Simsek
2016	—	`conf`	Decision Heuristics for Comparison: How Good Are They? IDM@NIPS Marcus Buckmann, Özgür Simsek
2016	—	`conf`	On Learning Decision Heuristics. IDM@NIPS Özgür Simsek, Marcus Buckmann
2016	—	`conf`	Simple Regression Models. IDM@NIPS Jan Malte Lichtenberg, Özgür Simsek
2016	A*	`conf`	Why Most Decisions Are Easy in Tetris - And Perhaps in Other Sequential Decision Problems, As Well. ICML Özgür Simsek, Simón Algorta, Amit Kothiyal
2015	—	`conf`	Learning From Small Samples: An Analysis of Simple Decision Heuristics. NIPS Özgür Simsek, Marcus Buckmann
2013	—	`conf`	Linear decision rule as aspiration for simple decision heuristics. NIPS Özgür Simsek
2009	A*	`conf`	Workshop summary: Abstraction in reinforcement learning. ICML Özgür Simsek
2008	J	`jnl`	Navigating networks by using homophily and degree. Proc. Natl. Acad. Sci. USA Özgür Simsek, David D. Jensen
2008	—	`conf`	Skill Characterization Based on Betweenness. NIPS Özgür Simsek, Andrew G. Barto
2006	A*	`conf`	An intrinsic reward mechanism for efficient exploration. ICML Özgür Simsek, Andrew G. Barto
2005	A*	`conf`	Decentralized Search in Networks Using Homophily and Degree Disparity. IJCAI Özgür Simsek, David D. Jensen
2005	A*	`conf`	Identifying useful subgoals in reinforcement learning by local graph partitioning. ICML Özgür Simsek, Alicia P. Wolfe, Andrew G. Barto
2005	—	`conf`	Learning Skills in Reinforcement Learning Using Relative Novelty. SARA Özgür Simsek, Andrew G. Barto
2005	A*	`conf`	Towards Competence in Autonomous Agents. AAAI Özgür Simsek
2005	A*	`conf`	Using relational knowledge discovery to prevent securities fraud. KDD Jennifer Neville, Özgür Simsek, David D. Jensen, John Komoroske, Kelly Palmer, Henry G. Goldberg
2004	A*	`conf`	Using relative novelty to identify useful temporal abstractions in reinforcement learning. ICML Özgür Simsek, Andrew G. Barto