About

My name is Emil Carlsson and I currently work as a Research Scientist at Sleep Cycle. I hold a PhD in Computer Science from Chalmers University of Technology and I specialize in machine learning and decision-making under uncertainty, focusing on developing reliable data-driven decision-making systems. My primary research interest lies in reinforcement learning, a computational framework for decision-making under uncertainty.

For an updated list of my publications, see my Google Scholar profile.

PhD Thesis

Reinforcement Learning: Efficient Communication and Sample Efficient Learning

Selected Publications

Active preference learning for ordering items in- and out-of-sample. Herman Bergström, Emil Carlsson, Devdatt Dubhashi, Fredrik D. Johansson. First two authors contributed equally. NeurIPS 2024. Code.

Pure exploration in bandits with linear constraints. Emil Carlsson, Debabrota Basu, Fredrik D. Johansson, Devdatt Dubhashi. International Conference on Artificial Intelligence and Statistics (AISTATS), 2024. Code.

Cultural evolution via iterated learning and communication explains effcient color naming systems. Emil Carlsson, Devdatt Dubhashi, Terry Regier. Journal of Language Evolution, 2024. Earlier version in Proceedings of the Annual Meeting of the Cognitive Science Society (CogSci) 45, 2023.Code. Earlier version

Publications

Active preference learning for ordering items in- and out-of-sample. Herman Bergström, Emil Carlsson, Devdatt Dubhashi, Fredrik D. Johansson. First two authors contributed equally. NeurIPS 2024. Code.

Pure exploration in bandits with linear constraints. Emil Carlsson, Debabrota Basu, Fredrik D. Johansson, Devdatt Dubhashi. International Conference on Artificial Intelligence and Statistics (AISTATS), 2024. Code.

Cultural evolution via iterated learning and communication explains efficient color naming systems. Emil Carlsson and Devdatt Dubhashi and Terry Regier. Preprint 2024. Code.

Identifiable latent bandits: Combining observational data and exploration for personalized healthcare. Ahmet Zahid Balcıoglu, Emil Carlsson, and Fredrik D. Johansson. ICML Workshop: Foundations of Reinforcement Learning and Control – Connections and Perspectives, 2024.

Learning Effcient Recursive Numeral Systems via Reinforcement Learning. Jonathan David Thomas, Andrea Silvi, Devdatt Dubhashi, Emil Carlsson, and Moa Johansson. AI for Math Workshop @ ICML, 2024.

Cultural evolution via iterated learning and communication explains effcient color naming systems. Emil Carlsson, Devdatt Dubhashi, Terry Regier. Journal of Language Evolution, 2024. Earlier version in Proceedings of the Annual Meeting of the Cognitive Science Society (CogSci) 45, 2023.Code. Earlier version

Fast Treatment Personalization with Latent Bandits in Fixed-Confidence Pure Exploration. Newton Mwai Kinyanjui, Emil Carlsson, and Fredrik D. Johansson. Transactions on Machine Learning Research (TMLR), 2023. Code.

Towards Learning Abstractions via Reinforcement Learning. Erik Jergéus, Leo Karlsson Oinonen, Emil Carlsson, and Moa Johansson. 8th International Workshop on Artificial Intelligence and Cognition (AIC), 2022.

Pragmatic reasoning in structured signaling games. Emil Carlsson, Devdatt Dubhashi. Proceedings of the Annual Meeting of the Cognitive Science Society (CogSci) , 44, 2022

Thompson sampling for bandits with clustered arms. Emil Carlsson, Fredrik D. Johansson, Devdatt Dubhashi. Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI), 2021.

Learning approximate and exact numeral systems via reinforcement learning. Emil Carlsson, Fredrik D. Johansson, Devdatt Dubhashi. Proceedings of the Annual Meeting of the Cognitive Science Society (CogSci) , 43 2021.

A reinforcement learning approach to efficient communication. Mikael Kågebäck, Emil Carlsson, Devdatt Dubhashi, Asad Sayeed. PLoS ONE, 15(7):1–26, 2020. Code.