Philip Amortila

26 papers A* 8A 1B 1Journal 14Unranked 2

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	A Unifying View of Coverage in Linear Off-Policy Evaluation. CoRR Philip Amortila, Audrey Huang, Akshay Krishnamurthy, Nan Jiang
2025	J	`jnl`	Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol. CoRR Pai Liu, Lingfeng Zhao, Shivangi Agarwal, Jinghan Liu, Audrey Huang, Philip Amortila, Nan Jiang
2024	A*	`conf`	Harnessing Density Ratios for Online Reinforcement Learning. ICLR Philip Amortila, Dylan J. Foster, Nan Jiang, Ayush Sekhari, Tengyang Xie
2024	J	`jnl`	Harnessing Density Ratios for Online Reinforcement Learning. CoRR Philip Amortila, Dylan J. Foster, Nan Jiang, Ayush Sekhari, Tengyang Xie
2024	A*	`conf`	Mitigating Covariate Shift in Misspecified Regression with Applications to Reinforcement Learning. COLT Philip Amortila, Tongyi Cao, Akshay Krishnamurthy
2024	J	`jnl`	Mitigating Covariate Shift in Misspecified Regression with Applications to Reinforcement Learning. CoRR Philip Amortila, Tongyi Cao, Akshay Krishnamurthy
2024	A*	`conf`	Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity. NeurIPS Philip Amortila, Dylan J. Foster, Nan Jiang, Akshay Krishnamurthy, Zakaria Mhammedi
2024	J	`jnl`	Reinforcement Learning under Latent Dynamics: Toward Statistical and Algorithmic Modularity. CoRR Philip Amortila, Dylan J. Foster, Nan Jiang, Akshay Krishnamurthy, Zakaria Mhammedi
2024	A*	`conf`	Scalable Online Exploration via Coverability. ICML Philip Amortila, Dylan J. Foster, Akshay Krishnamurthy
2024	J	`jnl`	Scalable Online Exploration via Coverability. CoRR Philip Amortila, Dylan J. Foster, Akshay Krishnamurthy
2023	A*	`conf`	The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation. ICML Philip Amortila, Nan Jiang, Csaba Szepesvári
2023	J	`jnl`	The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation. CoRR Philip Amortila, Nan Jiang, Csaba Szepesvári
2022	A*	`conf`	A Few Expert Queries Suffices for Sample-Efficient RL with Resets and Linear Value Approximation. NeurIPS Philip Amortila, Nan Jiang, Dhruv Madeka, Dean P. Foster
2022	J	`jnl`	A Few Expert Queries Suffices for Sample-Efficient RL with Resets and Linear Value Approximation. CoRR Philip Amortila, Nan Jiang, Dhruv Madeka, Dean P. Foster
2021	B	`conf`	Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions. ALT Gellért Weisz, Philip Amortila, Csaba Szepesvári
2021	A*	`conf`	On Query-efficient Planning in MDPs under Linear Realizability of the Optimal State-value Function. COLT Gellért Weisz, Philip Amortila, Barnabás Janzer, Yasin Abbasi-Yadkori, Nan Jiang, Csaba Szepesvári
2021	J	`jnl`	On Query-efficient Planning in MDPs under Linear Realizability of the Optimal State-value Function. CoRR Gellért Weisz, Philip Amortila, Barnabás Janzer, Yasin Abbasi-Yadkori, Nan Jiang, Csaba Szepesvári
2020	A	`conf`	A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms. AISTATS Philip Amortila, Doina Precup, Prakash Panangaden, Marc G. Bellemare
2020	J	`jnl`	A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms. CoRR Philip Amortila, Doina Precup, Prakash Panangaden, Marc G. Bellemare
2020	J	`jnl`	A Variant of the Wang-Foster-Kakade Lower Bound for the Discounted Setting. CoRR Philip Amortila, Nan Jiang, Tengyang Xie
2020	A*	`conf`	Constrained Markov Decision Processes via Backward Value Functions. ICML Harsh Satija, Philip Amortila, Joelle Pineau
2020	J	`jnl`	Constrained Markov Decision Processes via Backward Value Functions. CoRR Harsh Satija, Philip Amortila, Joelle Pineau
2020	J	`jnl`	Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions. CoRR Gellért Weisz, Philip Amortila, Csaba Szepesvári
2019	—	`conf`	Temporally Extended Metrics for Markov Decision Processes. SafeAI@AAAI Philip Amortila, Marc G. Bellemare, Prakash Panangaden, Doina Precup
2018	—	`conf`	Learning Graph Weighted Models on Pictures. ICGI Philip Amortila, Guillaume Rabusseau
2018	J	`jnl`	Learning Graph Weighted Models on Pictures. CoRR Philip Amortila, Guillaume Rabusseau