EB
Emma Brunskill
cs.LGcs.AIstat.MLcs.CLcs.CYcs.HCstat.MEstat.APcs.MAcs.RO
On Valency
published · living versionsW_een6xanw·v1 · currentpublished
Off-Policy Policy Gradient with State Distribution Correction
with Yao Liu, Adith Swaminathan, Alekh Agarwal
1 version
Preprints & journals
112 papers in the corpus · 2008–2026Generative Policy Improvement from Observational Data2610.23436v1 · Jonas Schweisthal, Dennis Frauen, Stefan Feuerriegel et al.2026 · 0 citationsarXiv
Inference on the Value of Policy Improvement in Adaptive Experiments2610.15789v1 · Justin Whitehouse, Emma Brunskill, Vasilis Syrgkanis2026 · 0 citationsarXiv
Mitigating Social Sycophancy via Pluralistic Preference Optimization2610.02568v2 · Stephane Hatgis-Kessell, Myra Cheng, Xiaoxuan Hou et al.2026 · 0 citationsarXiv
Specifying Reward Functions for RL Without Environment Sampling2609.15544v1 · Stephane Hatgis-Kessell, W. Bradley Knox, Emma Brunskill2026 · 0 citationsarXiv
Discovering High-Quality Chess Puzzles with Offline Reinforcement Learning2608.14851v1 · Allen Nie, Anirudhan Badrinath, Nicholas Tomlin et al.2026 · 0 citationsarXiv
A statistical test for the benefits of personalizing interventions.42424443 · Li, Zhaoqi, Brunskill, Emma2026 · 0 citationsScience (New York, N.Y.). 2026;393(6807):eaeb9506
When are LLMs Sufficient Policy Optimizers for Sequential RL Tasks?2605.30719v2 · Stephane Hatgis-Kessell, Emma Brunskill2026 · 0 citationsarXiv
Active Learning for Stochastic Contextual Linear Bandits2605.24803v1 · Emma Brunskill, Ishani Karmarkar, Zhaoqi Li2026 · 0 citationsarXiv
Improving Hybrid Human-AI Tutoring by Differentiating Human Tutor Roles Based on Student Needs2605.11155v1 · Ashish Gurung, Ge Gao, Jordan Gutterman et al.2026 · 0 citationsIn Proceedings of the 19th International Conference on Educational Data Mining 2026
Trading off rewards and errors in multi-armed bandits2605.00488v1 · Akram Erraqabi, Alessandro Lazaric, Michal Valko et al.2026 · 11 citationsarXiv
GIANTS: Generative Insight Anticipation from Scientific Literature2604.09793v1 · Joy He-Yueya, Anikait Singh, Ge Gao et al.2026 · 0 citationsarXiv
Generative Experiences for Digital Mental Health Interventions: Evidence from a Randomized Study2604.07558v3 · Ananya Bhattacharjee, Michael Liut, Matthew Jorke et al.2026 · 0 citationsarXiv
Computer-assisted learning in the real world: How Khan Academy influences student math learning.41481459 · Eames, Taryn, Brunskill, Emma, Yamkovenko, Bogdan et al.2026 · 4 citationsProceedings of the National Academy of Sciences of the United States of America. 2026;123(1):e2507708123
Repairing Reward Functions with Feedback to Mitigate Reward Hacking2510.13036v2 · Stephane Hatgis-Kessell, Logan Mondal Bhamidipaty, Emma Brunskill2025 · 0 citationsarXiv
Bloom: Designing for LLM-Augmented Behavior Change Interactions2510.05449v2 · Matthew Jorke, Defne Genc, Valentin Teutschbein et al.2025 · 8 citationsarXiv
Automated reminders reduce incarceration for missed court dates: Evidence from a text message experiment.41032609 · Chohlas-Wood, Alex, Coots, Madison, Nudell, Joe et al.2025 · 3 citationsScience advances. 2025;11(40):eadx7483
Assessing the Quality of AI-Generated Exams: A Large-Scale Field Study2508.08314v1 · Calvin Isley, Joshua Gilbert, Evangelos Kassos et al.2025 · 5 citationsarXiv
PERRY: Policy Evaluation with Confidence Intervals using Auxiliary Data2507.20068v3 · Aishwarya Mandyam, Jason Meng, Ge Gao et al.2025 · 0 citationsarXiv
Efficient RL for optimizing conversation level outcomes with an LLM-based tutor2507.16252v1 · Hyunji Nam, Omer Gottesman, Amy Zhang et al.2025 · 0 citationsarXiv
Can LLM-Simulated Practice and Feedback Upskill Human Counselors? A Randomized Study with 90+ Novice Counselors2505.02428v2 · Ryan Louie, Raj Sanjay Shah, Ifdita Hasan Orney et al.2025 · 8 citationsarXiv
Predicting Long Term Sequential Policy Value Using Softer Surrogates2412.20638v2 · Hyunji Nam, Allen Nie, Ge Gao et al.2024 · 0 citationsarXiv
Predicting Long-Term Student Outcomes from Short-Term EdTech Log Data2412.15473v2 · Ge Gao, Amelia Leon, Andrea Jetten et al.2024 · 5 citationsarXiv
Evaluating Treatment Prioritization Rules via Rank-Weighted Average Treatment Effects.40248684 · Yadlowsky, Steve, Fleming, Scott, Shah, Nigam et al.2026 · 74 citationsJournal of the American Statistical Association. 2025;120(549):38-51
Psychometric Alignment: Capturing Human Knowledge Distributions via Language Models2407.15645v1 · Joy He-Yueya, Wanjing Anya Ma, Kanishk Gandhi et al.2024 · 2 citationsarXiv
Short-Long Policy Evaluation with Novel Actions2407.03674v2 · Hyunji Alex Nam, Yash Chandak, Emma Brunskill2024 · 0 citationsarXiv
Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principles2407.00870v2 · Ryan Louie, Ananjan Nandi, William Fang et al.2024 · 59 citationsarXiv
OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators2405.17708v2 · Allen Nie, Yash Chandak, Christina J. Yuan et al.2024 · 1 citationarXiv
GPTCoach: Towards LLM-Based Physical Activity Coaching2405.06061v2 · Matthew Jorke, Shardul Sapkota, Lyndsea Warkenthien et al.2024 · 56 citationsarXiv
Data-driven Error Estimation: Excess Risk Bounds without Class Complexity as Input2405.04636v4 · Sanath Kumar Krishnamurthy, Anna Lyubarskaja, Emma Brunskill et al.2024 · 0 citationsarXiv
The GPT Surprise: Offering Large Language Model Chat in a Massive Coding Class Reduced Engagement but Increased Adopters Exam Performances2407.09975v2 · Allen Nie, Yash Chandak, Miroslav Suzara et al.2024 · 18 citationsarXiv
MedAlign: A Clinician-Generated Dataset for Instruction Following with Electronic Medical Records.41584261 · Fleming, Scott L, Lozano, Alejandro, Haberkorn, William J et al.2026 · 65 citationsProceedings of the ... AAAI Conference on Artificial Intelligence. AAAI Conference on Artificial Intelligence. 2024;38(20):22021-22030
Evaluating and Optimizing Educational Content with Large Language Model Judgments2403.02795v2 · Joy He-Yueya, Noah D. Goodman, Emma Brunskill2024 · 2 citationsarXiv
Minimax-Regret Sample Selection in Randomized Experiments2403.01386v2 · Yuchen Hu, Henry Zhu, Emma Brunskill et al.2024 · 2 citationsarXiv
Experiment Planning with Function Approximation2401.05193v1 · Aldo Pacchiano, Jonathan N. Lee, Emma Brunskill2024 · 1 citationarXiv
Improving Student Learning with Hybrid Human-AI Tutoring: A Three-Study Quasi-Experimental Investigation2312.11274v3 · Danielle R. Thomas, Jionghao Lin, Erin Gatz et al.2023 · 61 citationsarXiv
Adaptive Instrument Design for Indirect Experiments2312.02438v1 · Yash Chandak, Shiv Shankar, Vasilis Syrgkanis et al.2023 · 0 citationsarXiv
Adaptive Interventions with User-Defined Goals for Health Behavior Change2311.09483v4 · Aishwarya Mandyam, Matthew Jorke, William Denton et al.2023 · 1 citationarXiv
Proportional Response: Contextual Bandits for Simple and Cumulative Regret Minimization2307.02108v3 · Sanath Kumar Krishnamurthy, Ruohan Zhan, Susan Athey et al.2023 · 3 citationsarXiv
Supervised Pretraining Can Learn In-Context Reinforcement Learning2306.14892v1 · Jonathan N. Lee, Annie Xie, Aldo Pacchiano et al.2023 · 7 citationsarXiv
Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets2306.14069v2 · Anirudhan Badrinath, Yannis Flet-Berliac, Allen Nie et al.2023 · 6 citationsarXiv
Reinforcement Learning Tutor Better Supported Lower Performers in a Math Task2304.04933v2 · Sherry Ruan, Allen Nie, William Steenbergen et al.2023 · 27 citationsarXiv
Estimating Optimal Policy Value in General Linear Contextual Bandits2302.09451v1 · Jonathan N. Lee, Weihao Kong, Aldo Pacchiano et al.2023 · 0 citationsarXiv
Model-based Offline Reinforcement Learning with Local Misspecification2301.11426v1 · Kefan Dong, Yannis Flet-Berliac, Allen Nie et al.2023 · 0 citationsarXiv
Off-Policy Evaluation for Action-Dependent Non-Stationary Environments2301.10330v1 · Yash Chandak, Shiv Shankar, Nathaniel D. Bastian et al.2023 · 4 citationsarXiv
Giving Feedback on Interactive Student Programs with Meta-Exploration2211.08802v1 · Evan Zheran Liu, Moritz Stephan, Allen Nie et al.2022 · 3 citationsarXiv
Oracle Inequalities for Model Selection in Offline Reinforcement Learning2211.02016v1 · Jonathan N. Lee, George Tucker, Ofir Nachum et al.2022 · 1 citationarXiv
Data-Efficient Pipeline for Offline Reinforcement Learning with Limited Data2210.08642v2 · Allen Nie, Yannis Flet-Berliac, Deon R. Jordan et al.2022 · 2 citationsarXiv
Offline Policy Optimization with Eligible Actions2207.00632v1 · Yao Liu, Yannis Flet-Berliac, Emma Brunskill2022 · 0 citationsarXiv
Constraint Sampling Reinforcement Learning: Incorporating Expertise For Faster Learning2112.15221v1 · Tong Mu, Georgios Theocharous, David Arbour et al.2021 · 6 citationsAAAI2022
Identification of Subgroups With Similar Benefits in Off-Policy Policy Evaluation2111.14272v1 · Ramtin Keramati, Omer Gottesman, Leo Anthony Celi et al.2021 · 1 citationarXiv
Career total: 284 works. 112 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.