Scholar
Philip Amortila
Google Scholar ID: NZQkB8sAAAAJ
University of Illinois, Urbana-Champaign
Citations & Impact
Citations
329
H-index
8
i10-index
7
Publications
16
Co-authors
0
Contact
Publications
Resume (English only)
Academic Achievements
- - Publications:
- * Model Selection for Off-Policy Evaluation: New Algorithms and Experimental Protocol (NeurIPS 2025)
- * Reinforcement Learning under Latent Dynamics: Toward Statistical and Algorithmic Modularity (NeurIPS 2024)
- * Mitigating Covariate Shift in Misspecified Regression with Applications to Reinforcement Learning (COLT 2024)
- * Scalable Online Exploration via Coverability (ICML 2024)
- * Harnessing Density Ratios for Online Reinforcement Learning (ICLR 2024)
- * The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation (ICML 2023)
- * A Few Expert Queries Suffices for Sample-Efficient RL with Resets and Linear Value Approximation (NeurIPS 2022)
- * On Query-efficient Planning in MDPs under Linear Realizability of the Optimal State-value Function (COLT 2021)
- * Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions (ALT 2021, Best Student Paper Award)
- * Solving Constrained Markov Decision Processes via Backward Value Functions (ICML 2020)
Research Experience
- - 2025 - 2027: Postdoctoral Fellow at Simons Institute for the Theory of Computing, UC Berkeley, Advisors: Peter Bartlett and Jason D. Lee
- - 2023: Research Intern at Microsoft Research, New England, Advisors: Dylan Foster and Akshay Krishnamurthy
- - 2021 & 2022: Research Intern at Amazon Research, New York, Advisor: Dean P. Foster
- - 2020 & 2021: Visiting Researcher at the University of Alberta, Advisor: Csaba Szepesvári
Education
- - 2019 - 2025: PhD in Computer Science at the University of Illinois, Urbana-Champaign, Advisor: Nan Jiang
- - 2017 - 2019: MSc in Computer Science at McGill University, Advisors: Prakash Panangaden and Marc G. Bellemare
- - 2013 - 2017: BSc in Honours Maths & Physics at McGill University, Distinctions: First Class Honours, Principal’s Student-Athlete Honour Roll
Background
- - Research Interests: Statistical Reinforcement Learning
- - Field: Computer Science
- - Brief Introduction: Currently a postdoc at the Simons Institute for the Theory of Computing at UC Berkeley, working with Peter Bartlett and Jason D. Lee. In 2027, will join the faculty in the School of Computer Science at the University of Sydney.
Co-authors