Michael A. Osborne

On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations

Dec 28, 2022
Tim G. J. Rudner, Cong Lu, Michael A. Osborne, Yarin Gal, Yee Whye Teh

Figure 2 for On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations

Figure 3 for On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations

Figure 4 for On Pathologies in KL-Regularized Reinforcement Learning from Expert Demonstrations

* Published in Advances in Neural Information Processing Systems 34 (NeurIPS 2021)

Access Paper or Ask Questions

Bayesian Model Selection of Lithium-Ion Battery Models via Bayesian Quadrature

Nov 13, 2022
Masaki Adachi, Yannick Kuhn, Birger Horstmann, Arnulf Latz, Michael A. Osborne, David A. Howey

Figure 2 for Bayesian Model Selection of Lithium-Ion Battery Models via Bayesian Quadrature

Figure 3 for Bayesian Model Selection of Lithium-Ion Battery Models via Bayesian Quadrature

Figure 4 for Bayesian Model Selection of Lithium-Ion Battery Models via Bayesian Quadrature

* 11 pages, 2 figures, submitted to IFAC2023

Access Paper or Ask Questions

Bayesian Optimization over Discrete and Mixed Spaces via Probabilistic Reparameterization

Oct 18, 2022
Samuel Daulton, Xingchen Wan, David Eriksson, Maximilian Balandat, Michael A. Osborne, Eytan Bakshy

Figure 2 for Bayesian Optimization over Discrete and Mixed Spaces via Probabilistic Reparameterization

Figure 3 for Bayesian Optimization over Discrete and Mixed Spaces via Probabilistic Reparameterization

Figure 4 for Bayesian Optimization over Discrete and Mixed Spaces via Probabilistic Reparameterization

* To appear in Advances in Neural Information Processing Systems 35, 2022. Code available at: https://github.com/facebookresearch/bo_pr

Access Paper or Ask Questions

Log-Linear-Time Gaussian Processes Using Binary Tree Kernels

Oct 04, 2022
Michael K. Cohen, Samuel Daulton, Michael A. Osborne

Figure 2 for Log-Linear-Time Gaussian Processes Using Binary Tree Kernels

Figure 3 for Log-Linear-Time Gaussian Processes Using Binary Tree Kernels

Figure 4 for Log-Linear-Time Gaussian Processes Using Binary Tree Kernels

* NeurIPS 2022; 9 pages + appendices

Access Paper or Ask Questions

Bayesian Generational Population-Based Training

Jul 19, 2022
Xingchen Wan, Cong Lu, Jack Parker-Holder, Philip J. Ball, Vu Nguyen, Binxin Ru, Michael A. Osborne

Figure 2 for Bayesian Generational Population-Based Training

Figure 3 for Bayesian Generational Population-Based Training

Figure 4 for Bayesian Generational Population-Based Training

* AutoML Conference 2022. 10 pages, 4 figure, 3 tables (28 pages, 10 figures, 7 tables including references and appendices)

Access Paper or Ask Questions