- Home
- People
- Past Members of ACEMS
- Yasin Abbasi-Yadkori
Dr Yasin Abbasi-Yadkori
Research Fellow
Queensland University of Technology
Artificial intelligence, machine learning, sequential decision problems, sampling and optimization
Research Interests:
Artifical Intelligence
Machine Learning
Sampling and Optimization
Sequential Decision Problems
Publications
Invited talks, refereed proceedings and other conference outputs
Abbasi-Yadkori, Y., Bartlett P.L., Gabillon V., Malek A., & Valko M.
(2018). Best of both worlds: Stochastic & adversarial best-arm identification.
COLT, Conference on Learning Theory. 75, 918-949.
Abbasi-Yadkori, Y., Bartlett P.L., Gabillon V., & Malek A.
(2017). Hit-and-Run for Sampling and Planning in Non-Convex Spaces..
20th International Conference on Artifi- cial Intelligence and Statistics (AISTATS) 2017.
Abbasi-Yadkori, Y., Bartlett P.L., & Gabillon V.
(2017). Near Minimax Optimal Players for the Finite-Time3-Expert Prediction Problem.
31st Conference on Neural Information Processing Systems.
Malek, A., Koolen W. M., Abbasi-Yadkori Y., & Bartlett P.L.
(2015). Minimax time series prediction.
Advances in Neural Information Processing Systems.
Abbasi-Yadkori, Y., Bartlett P., Chen X., & Malek A.
(2015). Large-scale markov decision problems with KL control cost and its application to crowdsourcing.
32nd International Conference on Machine Learning.
Journal Articles
Abbasi-Yadkori, Y., Bartlett P.L., & Gabillon V.
(2016). Hit-and-run for sampling and planning in non-convex spaces.
arxiv.org.