Exponential Lower Bounds for Planning in MDPs With Linearly-Realizable Optimal Action-Value Functions G Weisz, P Amortila, C Szepesvári International Conference on Algorithmic Learning Theory (ALT) 2021, 2020 | 94 | 2020 |
Constrained Markov Decision Processes via Backward Value Functions H Satija, P Amortila, J Pineau International Conference on Machine Learning (ICML) 2020, 2020 | 66 | 2020 |
A Variant of the Wang-Foster-Kakade Lower Bound for the Discounted Setting P Amortila, N Jiang, T Xie arXiv preprint arXiv:2011.01075, 2020 | 24 | 2020 |
On Query-efficient Planning in MDPs under Linear Realizability of the Optimal State-value Function G Weisz, P Amortila, B Janzer, Y Abbasi-Yadkori, N Jiang, C Szepesvári Annual Conference on Learning Theory (COLT) 2021, 2021 | 22 | 2021 |
A Distributional Analysis of Sampling-Based Reinforcement Learning Algorithms P Amortila, D Precup, P Panangaden, MG Bellemare International Conference on Artificial Intelligence and Statistics (AISTATS …, 2020 | 15 | 2020 |
A Few Expert Queries Suffices for Sample-Efficient RL with Resets and Linear Value Approximation P Amortila, N Jiang, D Madeka, DP Foster NeurIPS 2022, 2022 | 5 | 2022 |
Harnessing Density Ratios for Online Reinforcement Learning P Amortila, DJ Foster, N Jiang, A Sekhari, T Xie ICLR 2024, 2024 | 4 | 2024 |
Temporally Extended Metrics for Markov Decision Processes. P Amortila, MG Bellemare, P Panangaden, D Precup AAAI 2019 Safety in AI workshop, 2019 | 4 | 2019 |
Scalable Online Exploration via Coverability P Amortila, DJ Foster, A Krishnamurthy arXiv preprint arXiv:2403.06571, 2024 | 1 | 2024 |
Mitigating Covariate Shift in Misspecified Regression with Applications to Reinforcement Learning P Amortila, T Cao, A Krishnamurthy arXiv preprint arXiv:2401.12216, 2024 | 1 | 2024 |
The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation P Amortila, N Jiang, C Szepesvari ICML 2023, 2023 | 1 | 2023 |
Couplings in Reinforcement Learning: Applications to State Abstraction and Algorithm Analysis P Amortila McGill University, Masters Thesis, 2019 | 1 | 2019 |
Learning Graph Weighted Models on Pictures P Amortila, G Rabusseau International Conference on Grammatical Inference 2018, 2018 | | 2018 |