AA
Alekh Agarwal
cs.LGstat.MLcs.AImath.OCcs.CLcs.GTcs.ITmath.ITcs.HCcs.IR
On Valency
published · living versionsW_hktak6f3·v1 · currentpublished
Off-policy evaluation for slate recommendation
with Adith Swaminathan, Akshay Krishnamurthy, Miroslav Dudík, John Langford +2
1 version
Preprints & journals
103 papers in the corpus · 2009–2026Decentralized LLM Workflows via Sequential Auctions2610.22201v1 · Ian Gemp, Shubhendu Trivedi, Adam Fisch et al.2026 · 0 citationsarXiv
Price of Anarchy of First-Price Auctions in Agentic Markets2610.20587v1 · Shubhendu Trivedi, Jacob Eisenstein, Alekh Agarwal et al.2026 · 0 citationsarXiv
Use and Effects of LLMs in Peer Review: A Randomized Experiment and Survey at ICML 20262609.19420v1 · Sunnie S. Y. Kim, Wesley Hanwen Deng, Jennifer Wortman Vaughan et al.2026 · 0 citationsarXiv
CollabEval: Statistically Efficient Collaborative Model Evaluation via Matrix Completion2607.05046v1 · Adam Fisch, Daniel Deutsch, Joshua Maynez et al.2026 · 0 citationsarXiv
Multiple-Prediction-Powered Inference2603.27414v1 · Charlie Cowen-Breen, Alekh Agarwal, Stephen Bates et al.2026 · 0 citationsarXiv
Cost-Optimal Active AI Model Evaluation2506.07949v1 · Anastasios N. Angelopoulos, Jacob Eisenstein, Jonathan Berant et al.2025 · 0 citationsarXiv
Rethinking the Global Convergence of Softmax Policy Gradient with Linear Function Approximation: The Case of Multi-Armed Bandits2505.03155v2 · Max Qiushi Lin, Jincheng Mei, Matin Aghaei et al.2025 · 0 citationsarXiv
Ordering-based Conditions for Global Convergence of Policy Gradient Methods2504.02130v1 · Jincheng Mei, Bo Dai, Alekh Agarwal et al.2025 · 0 citationsarXiv
Peer reviews of peer reviews: A randomized controlled trial and other experiments.40173178 · Goldberg, Alexander, Stelmakh, Ivan, Cho, Kyunghyun et al.2025 · 18 citationsPloS one. 2025;20(4):e0320444
Mitigating Preference Hacking in Policy Optimization with Pessimism2503.06810v1 · Dhawal Gupta, Adam Fisch, Christoph Dann et al.2025 · 0 citationsarXiv
Optimizing Pre-Training Data Mixtures with Mixtures of Data Expert Models2502.15950v1 · Lior Belenki, Alekh Agarwal, Tianze Shi et al.2025 · 1 citationarXiv
Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates2502.07141v1 · Jincheng Mei, Bo Dai, Alekh Agarwal et al.2025 · 0 citationsarXiv
Design Considerations in Offline Preference-based RL2502.06861v1 · Alekh Agarwal, Christoph Dann, Teodor V. Marinov2025 · 0 citationsarXiv
Catoni Contextual Bandits are Robust to Heavy-tailed Rewards2502.02486v1 · Chenlu Ye, Yujia Jin, Alekh Agarwal et al.2025 · 0 citationsarXiv
Preserving Expert-Level Privacy in Offline Reinforcement Learning2411.13598v2 · Navodita Sharma, Vishnu Vinod, Abhradeep Thakurta et al.2024 · 0 citationsarXiv
Rewarding Progress: Scaling Automated Process Verifiers for LLM Reasoning2410.08146v1 · Amrith Setlur, Chirag Nagpal, Adam Fisch et al.2024 · 3 citationsarXiv
Conditional Language Policy: A General Framework for Steerable Multi-Objective Finetuning2407.15762v2 · Kaiwen Wang, Rahul Kidambi, Ryan Sullivan et al.2024 · 1 citationarXiv
Robust Preference Optimization through Reward Model Distillation2405.19316v2 · Adam Fisch, Jacob Eisenstein, Vicky Zayats et al.2024 · 1 citationarXiv
Offline Imitation Learning from Multiple Baselines with Applications to Compiler Optimization2403.19462v1 · Teodor V. Marinov, Alekh Agarwal, Mircea Trofin2024 · 0 citationsarXiv
Stochastic Gradient Succeeds for Bandits2402.17235v1 · Jincheng Mei, Zixin Zhong, Bo Dai et al.2024 · 0 citationsarXiv
More Benefits of Being Distributional: Second-Order Bounds for Reinforcement Learning2402.07198v1 · Kaiwen Wang, Owen Oertell, Alekh Agarwal et al.2024 · 0 citationsarXiv
A Minimaximalist Approach to Reinforcement Learning from Human Feedback2401.04056v2 · Gokul Swamy, Christoph Dann, Rahul Kidambi et al.2024 · 3 citationsarXiv
Theoretical guarantees on the best-of-n alignment policy2401.01879v3 · Ahmad Beirami, Alekh Agarwal, Jonathan Berant et al.2024 · 1 citationarXiv
Helping or Herding? Reward Model Ensembles Mitigate but do not Eliminate Reward Hacking2312.09244v3 · Jacob Eisenstein, Chirag Nagpal, Alekh Agarwal et al.2023 · 4 citationsarXiv
Efficient End-to-End Visual Document Understanding with Rationale Distillation2311.09612v2 · Wang Zhu, Alekh Agarwal, Mandar Joshi et al.2023 · 5 citationsarXiv
A Mechanism for Sample-Efficient In-Context Learning for Sparse Retrieval Tasks2305.17040v1 · Jacob Abernethy, Alekh Agarwal, Teodor V. Marinov et al.2023 · 1 citationarXiv
An Empirical Evaluation of Federated Contextual Bandit Algorithms2303.10218v1 · Alekh Agarwal, H. Brendan McMahan, Zheng Xu2023 · 0 citationsarXiv
Leveraging User-Triggered Supervision in Contextual Bandits2302.03784v1 · Alekh Agarwal, Claudio Gentile, Teodor V. Marinov2023 · 0 citationsarXiv
Learning in POMDPs is Sample-Efficient with Hindsight Observability2301.13857v2 · Jonathan N. Lee, Alekh Agarwal, Christoph Dann et al.2023 · 5 citationsarXiv
VOL: Towards Optimal Regret in Model-free RL with Nonlinear Function Approximation2212.06069v1 · Alekh Agarwal, Yujia Jin, Tong Zhang2022 · 0 citationsarXiv
On the Statistical Efficiency of Reward-Free Exploration in Non-Linear RL2206.10770v2 · Jinglin Chen, Aditya Modi, Akshay Krishnamurthy et al.2022 · 3 citationsarXiv
Model-based RL with Optimistic Posterior Sampling: Structural Conditions and Sample Complexity2206.07659v2 · Alekh Agarwal, Tong Zhang2022 · 3 citationsarXiv
Provable Benefits of Representational Transfer in Reinforcement Learning2205.14571v2 · Alekh Agarwal, Yuda Song, Wen Sun et al.2022 · 3 citationsarXiv
Non-Linear Reinforcement Learning in Large Action Spaces: Structural Conditions and Sample-efficiency of Posterior Sampling2203.08248v2 · Alekh Agarwal, Tong Zhang2022 · 2 citationsarXiv
Minimax Regret Optimization for Robust Machine Learning under Distribution Shift2202.05436v1 · Alekh Agarwal, Tong Zhang2022 · 3 citationsarXiv
Adversarially Trained Actor Critic for Offline Reinforcement Learning2202.02446v2 · Ching-An Cheng, Tengyang Xie, Nan Jiang et al.2022 · 21 citationsarXiv
Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning Approach2202.00063v3 · Xuezhou Zhang, Yuda Song, Masatoshi Uehara et al.2022 · 6 citationsarXiv
Provable RL with Exogenous Distractors via Multistep Inverse Dynamics2110.08847v2 · Yonathan Efroni, Dipendra Misra, Akshay Krishnamurthy et al.2021 · 3 citationsarXiv
Bellman-consistent Pessimism for Offline Reinforcement Learning2106.06926v6 · Tengyang Xie, Ching-An Cheng, Nan Jiang et al.2021 · 26 citationsarXiv
Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation2103.12923v2 · Andrea Zanette, Ching-An Cheng, Alekh Agarwal2021 · 5 citationsarXiv
Provably Correct Optimization and Exploration with Non-linear Policies2103.11559v1 · Fei Feng, Wotao Yin, Alekh Agarwal et al.2021 · 1 citationarXiv
Towards a Dimension-Free Understanding of Adaptive Linear Control2103.10620v2 · Juan C. Perdomo, Max Simchowitz, Alekh Agarwal et al.2021 · 2 citationsarXiv
Model-free Representation Learning and Exploration in Low-rank MDPs2102.07035v2 · Aditya Modi, Jinglin Chen, Akshay Krishnamurthy et al.2021 · 11 citationsarXiv
Provably Good Batch Reinforcement Learning Without Great Exploration2007.08202v2 · Yao Liu, Adith Swaminathan, Alekh Agarwal et al.2020 · 35 citationsarXiv
PC-PG: Policy Cover Directed Exploration for Provable Policy Gradient Learning2007.08459v2 · Alekh Agarwal, Mikael Henaff, Sham Kakade et al.2020 · 33 citationsarXiv
Policy Improvement via Imitation of Multiple Oracles2007.00795v2 · Ching-An Cheng, Andrey Kolobov, Alekh Agarwal2020 · 9 citationsarXiv
Safe Reinforcement Learning via Curriculum Induction2006.12136v2 · Matteo Turchetta, Andrey Kolobov, Shital Shah et al.2020 · 44 citationsarXiv
Optimizing Interactive Systems via Data-Driven Objectives2006.12999v1 · Ziming Li, Julia Kiseleva, Alekh Agarwal et al.2020 · 0 citationsarXiv
Reparameterized Variational Divergence Minimization for Stable Imitation2006.10810v1 · Dilip Arumugam, Debadeepta Dey, Alekh Agarwal et al.2020 · 2 citationsarXiv
FLAMBE: Structural Complexity and Representation Learning of Low Rank MDPs2006.10814v2 · Alekh Agarwal, Sham Kakade, Akshay Krishnamurthy et al.2020 · 43 citationsarXiv
Career total: 154 works. 103 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.