Below, you can find a list of my publications, with links to the published version and any supplementary material, preprints, and related code.
Please feel free to get in touch if you have any questions about my research.
We propose a novel characterisation of a multi-level skill hierarchy for reinforcement learning, based on hierarchical clustering of a graphical representation of an agent's interaction with its environment.
Recently accepted at NeurIPS 2023 - stay tuned for the camera-ready version!
Evans, J. B. and Şimşek, Ö. (2023) "Creating Multi-Level Skill Hierarchies in Reinforcement Learning". In 37th Conference on Neural Information Processing Systems (In Press).