publications

Conference and Journal Papers

2021

1. Learning Markov State Abstractions for Deep Reinforcement Learning

   Allen, Cameron, Parikh, Neev, Gottesman, Omer, and Konidaris, George

   Advances in Neural Information Processing Systems 2021
2. State Relevance for Off-Policy Evaluation

   Shen, Simon P, Ma, Yecheng, Gottesman, Omer, and Doshi-Velez, Finale

   In International Conference on Machine Learning 2021

2020

1. Learning to search efficiently for causally near-optimal treatments

   Håkansson, Samuel, Lindblom, Viktor, Gottesman, Omer, and Johansson, Fredrik D

   In Advances in Neural Information Processing Systems 2020
2. Interpretable off-policy evaluation in reinforcement learning by highlighting influential transitions

   Gottesman, Omer, Futoma, Joseph, Liu, Yao, Parbhoo, Sonali, Celi, Leo, Brunskill, Emma, and Doshi-Velez, Finale

   In International Conference on Machine Learning 2020

2019

1. Guidelines for reinforcement learning in healthcare

   Gottesman, Omer, Johansson, Fredrik, Komorowski, Matthieu, Faisal, Aldo, Sontag, David, Doshi-Velez, Finale, and Celi, Leo Anthony

   Nature medicine 2019
2. Combining parametric and nonparametric models for off-policy evaluation

   Gottesman, Omer, Liu, Yao, Sussex, Scott, Brunskill, Emma, and Doshi-Velez, Finale

   In International Conference on Machine Learning 2019

2018

1. Improving sepsis treatment strategies by combining deep and kernel-based reinforcement learning

   Peng, Xuefeng, Ding, Yi, Wihl, David, Gottesman, Omer, Komorowski, Matthieu, Lehman, Li-wei H, Ross, Andrew, Faisal, Aldo, and Doshi-Velez, Finale

   In AMIA Annual Symposium Proceedings 2018
2. Weighted tensor decomposition for learning latent variables with partial data

   Gottesman, Omer, Pan, Weiwei, and Doshi-Velez, Finale

   In International Conference on Artificial Intelligence and Statistics 2018
3. Representation Balancing MDPs for Off-policy Policy Evaluation

   Liu, Yao, Gottesman, Omer, Raghu, Aniruddh, Komorowski, Matthieu, Faisal, Aldo A, Doshi-Velez, Finale, and Brunskill, Emma

   Advances in Neural Information Processing Systems 2018
4. A state variable for crumpled thin sheets

   Omer, Gottesman, Jovana, Andrejevic, Rycroft, Chris H, and Rubinstein, Shmuel M

   Communications Physics 2018
5. Localized patterns in crushed conical shells

   Gottesman, Omer, Vouga, Etienne, Rubinstein, Shmuel M, and Mahadevan, L

   EPL (Europhysics Letters) 2018
6. Improving counterfactual reasoning with kernelised dynamic mixing models

   Parbhoo, Sonali, Gottesman, Omer, Ross, Andrew Slavin, Komorowski, Matthieu, Faisal, Aldo, Bon, Isabella, Roth, Volker, and Doshi-Velez, Finale

   PloS one 2018

2017

1. On the incompressibility of cylindrical origami patterns

   Bös, Friedrich, Wardetzky, Max, Vouga, Etienne, and Gottesman, Omer

   Journal of Mechanical Design 2017
2. Nonmonotonic aging and memory retention in disordered mechanical systems

   Lahini, Yoav, Gottesman, Omer, Amir, Ariel, and Rubinstein, Shmuel M

   Physical review letters 2017

2015

1. Furrows in the wake of propagating d-cones

   Gottesman, Omer, Efrati, Efi, and Rubinstein, Shmuel M

   Nature communications 2015

2014

1. Science with a wide-field UV transient explorer

   Sagiv, I, Gal-Yam, A, Ofek, EO, Waxman, E, Aharonson, O, Kulkarni, SR, Nakar, E, Maoz, D, Trakhtenbrot, B, Gottesman, O, Phinney, ES, and others,

   The Astronomical Journal 2014

2012

1. Multiple extinction routes in stochastic population models

   Gottesman, Omer, and Meerson, Baruch

   Physical Review E 2012

Workshops and Preprints

2021

1. Deep Q-Network with Proximal Iteration

   Asadi, Kavosh, Fakoor, Rasool, Gottesman, Omer, Littman, Michael L, and Smola, Alexander J

   arXiv preprint arXiv:2112.05848 2021
2. Identification of Subgroups With Similar Benefits in Off-Policy Policy Evaluation

   Keramati, Ramtin, Gottesman, Omer, Celi, Leo Anthony, Doshi-Velez, Finale, and Brunskill, Emma

   arXiv preprint arXiv:2111.14272 2021
3. Coarse-Grained Smoothness for RL in Metric Spaces

   Gottesman, Omer, Asadi, Kavosh, Allen, Cameron, Lobel, Sam, Konidaris, George, and Littman, Michael

   arXiv preprint arXiv:2110.12276 2021

2020

1. Shaping Control Variates for Off-Policy Evaluation

   Parbhoo, Sonali, Gottesman, Omer, and Doshi-Velez, Finale

   In Offline Reinforcement Learning Workshop at Neural Information Processing Systems (NeurIPS) 2020
2. Off-Policy Evaluation of Reinforcement Learning in Healthcare

   Gottesman, Omer

   In Offline Reinforcement Learning Workshop at Neural Information Processing Systems (NeurIPS) 2020

2019

1. A general method for regularizing tensor decomposition methods via pseudo-data

   Gottesman, Omer, Pan, Weiwei, and Doshi-Velez, Finale

   arXiv preprint arXiv:1905.10424 2019

2018

1. Evaluating reinforcement learning algorithms in observational health settings

   Gottesman, Omer, Johansson, Fredrik, Meier, Joshua, Dent, Jack, Lee, Donghun, Srinivasan, Srivatsan, Zhang, Linying, Ding, Yi, Wihl, David, Peng, Xuefeng, and others,

   arXiv preprint arXiv:1805.12298 2018
2. Behaviour policy estimation in off-policy policy evaluation: Calibration matters

   Raghu, Aniruddh, Gottesman, Omer, Liu, Yao, Komorowski, Matthieu, Faisal, Aldo, Doshi-Velez, Finale, and Brunskill, Emma

   International Conference on Machine Learning: workshop on Causal Machine Learning 2018
3. Stitched Trajectories for Off-Policy Learning

   Sussex, Scott, Gottesman, Omer, Liu, Yao, Murphy, Susan, Brunskill, Emma, and Doshi-Velez, Finale

   International Conference on Machine Learning: workshop on Causal Machine Learning 2018