Alekh Agarwal

ORCID

Publication Activity (10 Years)

Years Active: 2006-2024
Publications (10 Years): 125

Top Venues

University of California, Berkeley, USA (PHD)

Education History

University of California, Berkeley, USA

PHD

Publications

Jincheng Mei, Zixin Zhong, Bo Dai, Alekh Agarwal, Csaba Szepesvári, Dale Schuurmans
Stochastic Gradient Succeeds for Bandits. CoRR (2024)
Kaiwen Wang, Owen Oertell, Alekh Agarwal, Nathan Kallus, Wen Sun
More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning. CoRR (2024)
Gokul Swamy, Christoph Dann, Rahul Kidambi, Zhiwei Steven Wu, Alekh Agarwal
A Minimaximalist Approach to Reinforcement Learning from Human Feedback. CoRR (2024)
Adam Fisch, Jacob Eisenstein, Vicky Zayats, Alekh Agarwal, Ahmad Beirami, Chirag Nagpal, Petet Shaw, Jonathan Berant
Robust Preference Optimization through Reward Model Distillation. CoRR (2024)
Jacob D. Abernethy, Alekh Agarwal, Teodor Vanislavov Marinov, Manfred K. Warmuth
A Mechanism for Sample-Efficient In-Context Learning for Sparse Retrieval Tasks. ALT (2024)
Ahmad Beirami, Alekh Agarwal, Jonathan Berant, Alexander D'Amour, Jacob Eisenstein, Chirag Nagpal, Ananda Theertha Suresh
Theoretical guarantees on the best-of-n alignment policy. CoRR (2024)
Teodor V. Marinov, Alekh Agarwal, Mircea Trofin
Offline Imitation Learning from Multiple Baselines with Applications to Compiler Optimization. CoRR (2024)
Kaiwen Wang, Rahul Kidambi, Ryan Sullivan, Alekh Agarwal, Christoph Dann, Andrea Michi, Marco Gelmi, Yunxuan Li, Raghav Gupta, Avinava Dubey, Alexandre Ramé, Johan Ferret, Geoffrey Cideron, Le Hou, Hongkun Yu, Amr Ahmed, Aranyak Mehta, Léonard Hussenot, Olivier Bachem, Edouard Leurent
Conditioned Language Policy: A General Framework for Steerable Multi-Objective Finetuning. CoRR (2024)
Wang Zhu, Alekh Agarwal, Mandar Joshi, Robin Jia, Jesse Thomason, Kristina Toutanova
Efficient End-to-End Visual Document Understanding with Rationale Distillation. NAACL-HLT (2024)
Jincheng Mei, Bo Dai, Alekh Agarwal, Mohammad Ghavamzadeh, Csaba Szepesvári, Dale Schuurmans
Ordering-based Conditions for Global Convergence of Policy Gradient Methods. NeurIPS (2023)
Jacob D. Abernethy, Alekh Agarwal, Teodor V. Marinov, Manfred K. Warmuth
A Mechanism for Sample-Efficient In-Context Learning for Sparse Retrieval Tasks. CoRR (2023)
Jacob Eisenstein, Chirag Nagpal, Alekh Agarwal, Ahmad Beirami, Alex D'Amour, Dj Dvijotham, Adam Fisch, Katherine A. Heller, Stephen Pfohl, Deepak Ramachandran, Peter Shaw, Jonathan Berant
Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking. CoRR (2023)
Alexander Goldberg, Ivan Stelmakh, Kyunghyun Cho, Alice H. Oh, Alekh Agarwal, Danielle Belgrave, Nihar B. Shah
Peer Reviews of Peer Reviews: A Randomized Controlled Trial and Other Experiments. CoRR (2023)
Alekh Agarwal, Claudio Gentile, Teodor V. Marinov
Leveraging User-Triggered Supervision in Contextual Bandits. CoRR (2023)
Jincheng Mei, Zixin Zhong, Bo Dai, Alekh Agarwal, Csaba Szepesvári, Dale Schuurmans
Stochastic Gradient Succeeds for Bandits. ICML (2023)
Jonathan N. Lee, Alekh Agarwal, Christoph Dann, Tong Zhang
Learning in POMDPs is Sample-Efficient with Hindsight Observability. CoRR (2023)
Wang Zhu, Alekh Agarwal, Mandar Joshi, Robin Jia, Jesse Thomason, Kristina Toutanova
Efficient End-to-End Visual Document Understanding with Rationale Distillation. CoRR (2023)
Alekh Agarwal, Yujia Jin, Tong Zhang
VOQL: Towards Optimal Regret in Model-free RL with Nonlinear Function Approximation. COLT (2023)
Jonathan Lee, Alekh Agarwal, Christoph Dann, Tong Zhang
Learning in POMDPs is Sample-Efficient with Hindsight Observability. ICML (2023)
Alekh Agarwal, Yuda Song, Wen Sun, Kaiwen Wang, Mengdi Wang, Xuezhou Zhang
Provable Benefits of Representational Transfer in Reinforcement Learning. COLT (2023)
Alekh Agarwal, H. Brendan McMahan, Zheng Xu
An Empirical Evaluation of Federated Contextual Bandit Algorithms. CoRR (2023)
Jinglin Chen, Aditya Modi, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal
On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL. NeurIPS (2022)
Alekh Agarwal, Tong Zhang
Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Sampling. COLT (2022)
Alekh Agarwal, Tong Zhang
Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Sampling. CoRR (2022)
Ching-An Cheng, Tengyang Xie, Nan Jiang, Alekh Agarwal
Adversarially Trained Actor Critic for Offline Reinforcement Learning. ICML (2022)
Jinglin Chen, Aditya Modi, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal
On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL. CoRR (2022)
Xuezhou Zhang, Yuda Song, Masatoshi Uehara, Mengdi Wang, Alekh Agarwal, Wen Sun
Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning Approach. CoRR (2022)
Xuezhou Zhang, Yuda Song, Masatoshi Uehara, Mengdi Wang, Alekh Agarwal, Wen Sun
Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning approach. ICML (2022)
Alekh Agarwal, Tong Zhang
Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity. NeurIPS (2022)
Ching-An Cheng, Tengyang Xie, Nan Jiang, Alekh Agarwal
Adversarially Trained Actor Critic for Offline Reinforcement Learning. CoRR (2022)
Alekh Agarwal, Tong Zhang
Minimax Regret Optimization for Robust Machine Learning under Distribution Shift. CoRR (2022)
Alekh Agarwal, Yujia Jin, Tong Zhang
VOQL: Towards Optimal Regret in Model-free RL with Nonlinear Function Approximation. CoRR (2022)
Alekh Agarwal, Tong Zhang
Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity. CoRR (2022)
Alekh Agarwal, Yuda Song, Wen Sun, Kaiwen Wang, Mengdi Wang, Xuezhou Zhang
Provable Benefits of Representational Transfer in Reinforcement Learning. CoRR (2022)
Alekh Agarwal, Tong Zhang
Minimax Regret Optimization for Robust Machine Learning under Distribution Shift. COLT (2022)
Yonathan Efroni, Dipendra Misra, Akshay Krishnamurthy, Alekh Agarwal, John Langford
Provably Filtering Exogenous Distractors using Multistep Inverse Dynamics. ICLR (2022)
Andrea Zanette, Ching-An Cheng, Alekh Agarwal
Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation. CoRR (2021)
Andrea Zanette, Ching-An Cheng, Alekh Agarwal
Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation. COLT (2021)
Fei Feng, Wotao Yin, Alekh Agarwal, Lin F. Yang
Provably Correct Optimization and Exploration with Non-linear Policies. CoRR (2021)
Alekh Agarwal, Sham M. Kakade, Jason D. Lee, Gaurav Mahajan
On the Theory of Policy Gradient Methods: Optimality, Approximation, and Distribution Shift. J. Mach. Learn. Res. 22 (2021)
Yonathan Efroni, Dipendra Misra, Akshay Krishnamurthy, Alekh Agarwal, John Langford
Provable RL with Exogenous Distractors via Multistep Inverse Dynamics. CoRR (2021)
Tengyang Xie, Ching-An Cheng, Nan Jiang, Paul Mineiro, Alekh Agarwal
Bellman-consistent Pessimism for Offline Reinforcement Learning. CoRR (2021)
Juan C. Perdomo, Max Simchowitz, Alekh Agarwal, Peter L. Bartlett
Towards a Dimension-Free Understanding of Adaptive Linear Control. CoRR (2021)
Aditya Modi, Jinglin Chen, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal
Model-free Representation Learning and Exploration in Low-rank MDPs. CoRR (2021)
Fei Feng, Wotao Yin, Alekh Agarwal, Lin Yang
Provably Correct Optimization and Exploration with Non-linear Policies. ICML (2021)
Tengyang Xie, Ching-An Cheng, Nan Jiang, Paul Mineiro, Alekh Agarwal
Bellman-consistent Pessimism for Offline Reinforcement Learning. NeurIPS (2021)
Alberto Bietti, Alekh Agarwal, John Langford
A Contextual Bandit Bake-off. J. Mach. Learn. Res. 22 (2021)
Juan C. Perdomo, Max Simchowitz, Alekh Agarwal, Peter L. Bartlett
Towards a Dimension-Free Understanding of Adaptive Linear Control. COLT (2021)
Chen-Yu Wei, Haipeng Luo, Alekh Agarwal
Taking a hint: How to leverage loss predictors in contextual bandits? CoRR (2020)
Alekh Agarwal, Mikael Henaff, Sham M. Kakade, Wen Sun
PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning. CoRR (2020)
Alekh Agarwal, Sham M. Kakade, Akshay Krishnamurthy, Wen Sun
FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs. NeurIPS (2020)
Alekh Agarwal, Sham M. Kakade, Jason D. Lee, Gaurav Mahajan
Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes. COLT (2020)
Yao Liu, Adith Swaminathan, Alekh Agarwal, Emma Brunskill
Provably Good Batch Off-Policy Reinforcement Learning Without Great Exploration. NeurIPS (2020)
Matteo Turchetta, Andrey Kolobov, Shital Shah, Andreas Krause, Alekh Agarwal
Safe Reinforcement Learning via Curriculum Induction. NeurIPS (2020)
Chen-Yu Wei, Haipeng Luo, Alekh Agarwal
Taking a hint: How to leverage loss predictors in contextual bandits? COLT (2020)
Jordan T. Ash, Chicheng Zhang, Akshay Krishnamurthy, John Langford, Alekh Agarwal
Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds. ICLR (2020)
Yao Liu, Adith Swaminathan, Alekh Agarwal, Emma Brunskill
Provably Good Batch Reinforcement Learning Without Great Exploration. CoRR (2020)
Alekh Agarwal, Sham M. Kakade, Lin F. Yang
Model-Based Reinforcement Learning with a Generative Model is Minimax Optimal. COLT (2020)
Alekh Agarwal, Sham M. Kakade, Akshay Krishnamurthy, Wen Sun
FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs. CoRR (2020)
Dilip Arumugam, Debadeepta Dey, Alekh Agarwal, Asli Celikyilmaz, Elnaz Nouri, Bill Dolan
Reparameterized Variational Divergence Minimization for Stable Imitation. CoRR (2020)
Ziming Li, Julia Kiseleva, Alekh Agarwal, Maarten de Rijke, Ryen W. White
Optimizing Interactive Systems via Data-Driven Objectives. CoRR (2020)
Alekh Agarwal, John Langford, Chen-Yu Wei
Federated Residual Learning. CoRR (2020)
Aditya Modi, Debadeepta Dey, Alekh Agarwal, Adith Swaminathan, Besmira Nushi, Sean Andrist, Eric Horvitz
Metareasoning in Modular Software Systems: On-the-Fly Configuration Using Reinforcement Learning with Rich Contextual Representations. AAAI (2020)
Ching-An Cheng, Andrey Kolobov, Alekh Agarwal
Policy Improvement from Multiple Experts. CoRR (2020)
Ching-An Cheng, Andrey Kolobov, Alekh Agarwal
Policy Improvement via Imitation of Multiple Oracles. NeurIPS (2020)
Matteo Turchetta, Andrey Kolobov, Shital Shah, Andreas Krause, Alekh Agarwal
Safe Reinforcement Learning via Curriculum Induction. CoRR (2020)
Alekh Agarwal, Mikael Henaff, Sham M. Kakade, Wen Sun
PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning. NeurIPS (2020)
Aditya Grover, Jiaming Song, Ashish Kapoor, Kenneth Tran, Alekh Agarwal, Eric Horvitz, Stefano Ermon
Bias Correction of Learned Generative Models via Likelihood-free Importance Weighting. DGS@ICLR (2019)
Jordan T. Ash, Chicheng Zhang, Akshay Krishnamurthy, John Langford, Alekh Agarwal
Deep Batch Active Learning by Diverse, Uncertain Gradient Lower Bounds. CoRR (2019)
Aditya Grover, Jiaming Song, Alekh Agarwal, Kenneth Tran, Ashish Kapoor, Eric Horvitz, Stefano Ermon
Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting. CoRR (2019)
Alekh Agarwal, Sham M. Kakade, Lin F. Yang
On the Optimality of Sparse Model-Based Planning for Markov Decision Processes. CoRR (2019)
Alekh Agarwal, Miroslav Dudík, Zhiwei Steven Wu
Fair Regression: Quantitative Definitions and Reduction-Based Algorithms. ICML (2019)
Akshay Krishnamurthy, Alekh Agarwal, Tzu-Kuo Huang, Hal Daumé III, John Langford
Active Learning for Cost-Sensitive Classification. J. Mach. Learn. Res. 20 (2019)
Simon S. Du, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal, Miroslav Dudík, John Langford
Provably efficient RL with Rich Observations via Latent State Decoding. ICML (2019)
Alekh Agarwal, Sham M. Kakade, Jason D. Lee, Gaurav Mahajan
Optimality and Approximation with Policy Gradient Methods in Markov Decision Processes. CoRR (2019)
Alekh Agarwal, Miroslav Dudík, Zhiwei Steven Wu
Fair Regression: Quantitative Definitions and Reduction-based Algorithms. CoRR (2019)
Chicheng Zhang, Alekh Agarwal, Hal Daumé III, John Langford, Sahand N. Negahban
Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback. CoRR (2019)
Yao Liu, Adith Swaminathan, Alekh Agarwal, Emma Brunskill
Off-Policy Policy Gradient with Stationary Distribution Correction. UAI (2019)
Wen Sun, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford
Model-based RL in Contextual Decision Processes: PAC bounds and Exponential Improvements over Model-free Approaches. COLT (2019)
Aditya Grover, Jiaming Song, Ashish Kapoor, Kenneth Tran, Alekh Agarwal, Eric Horvitz, Stefano Ermon
Bias Correction of Learned Generative Models using Likelihood-Free Importance Weighting. NeurIPS (2019)
Aditya Modi, Debadeepta Dey, Alekh Agarwal, Adith Swaminathan, Besmira Nushi, Sean Andrist, Eric Horvitz
Metareasoning in Modular Software Systems: On-the-Fly Configuration using Reinforcement Learning with Rich Contextual Representations. CoRR (2019)
Yao Liu, Adith Swaminathan, Alekh Agarwal, Emma Brunskill
Off-Policy Policy Gradient with State Distribution Correction. CoRR (2019)
Simon S. Du, Akshay Krishnamurthy, Nan Jiang, Alekh Agarwal, Miroslav Dudík, John Langford
Provably efficient RL with Rich Observations via Latent State Decoding. CoRR (2019)
Chicheng Zhang, Alekh Agarwal, Hal Daumé III, John Langford, Sahand Negahban
Warm-starting Contextual Bandits: Robustly Combining Supervised and Bandit Feedback. ICML (2019)
Christoph Dann, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire
On Oracle-Efficient PAC RL with Rich Observations. NeurIPS (2018)
Hoang Minh Le, Nan Jiang, Alekh Agarwal, Miroslav Dudík, Yisong Yue, Hal Daumé III
Hierarchical Imitation and Reinforcement Learning. ICML (2018)
Alberto Bietti, Alekh Agarwal, John Langford
Practical Evaluation and Optimization of Contextual Bandit Algorithms. CoRR (2018)
Nan Jiang, Alekh Agarwal
Open Problem: The Dependence of Sample Complexity Lower Bounds on Planning Horizon. COLT (2018)
Dylan J. Foster, Alekh Agarwal, Miroslav Dudík, Haipeng Luo, Robert E. Schapire
Practical Contextual Bandits with Regression Oracles. ICML (2018)
Christoph Dann, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire
On Polynomial Time PAC Reinforcement Learning with Rich Observations. CoRR (2018)
Wen Sun, Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford
Model-Based Reinforcement Learning in Contextual Decision Processes. CoRR (2018)
Alekh Agarwal, Alina Beygelzimer, Miroslav Dudík, John Langford, Hanna M. Wallach
A Reductions Approach to Fair Classification. ICML (2018)
Alekh Agarwal, Alina Beygelzimer, Miroslav Dudík, John Langford, Hanna M. Wallach
A Reductions Approach to Fair Classification. CoRR (2018)
Dylan J. Foster, Alekh Agarwal, Miroslav Dudík, Haipeng Luo, Robert E. Schapire
Practical Contextual Bandits with Regression Oracles. CoRR (2018)
Hoang Minh Le, Nan Jiang, Alekh Agarwal, Miroslav Dudík, Yisong Yue, Hal Daumé III
Hierarchical Imitation and Reinforcement Learning. CoRR (2018)
Haipeng Luo, Chen-Yu Wei, Alekh Agarwal, John Langford
Efficient Contextual Bandits in Non-stationary Worlds. COLT (2018)
Akshay Krishnamurthy, Alekh Agarwal, Tzu-Kuo Huang, Hal Daumé III, John Langford
Active Learning for Cost-Sensitive Classification. ICML (2017)
Alekh Agarwal, Animashree Anandkumar, Praneeth Netrapalli
A Clustering Approach to Learning Sparsely Used Overcomplete Dictionaries. IEEE Trans. Inf. Theory 63 (1) (2017)
Nan Jiang, Akshay Krishnamurthy, Alekh Agarwal, John Langford, Robert E. Schapire
Contextual Decision Processes with low Bellman rank are PAC-Learnable. ICML (2017)
Alekh Agarwal, Akshay Krishnamurthy, John Langford, Haipeng Luo, Robert E. Schapire
Open Problem: First-Order Regret Bounds for Contextual Bandits. COLT (2017)

Alekh Agarwal.css-eqlu8i{font-size:small;padding-left:4px;}

Publication Activity (10 Years)

Top Topics

Top Venues

Alekh Agarwal