Emma Brunskill

Assessing the Quality of AI-Generated Exams: A Large-Scale Field Study AAAI 2026 Cost-Aware Near-Optimal Policy Learning AAAI 2025 OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators NIPS 2024 Adaptive Instrument Design for Indirect Experiments ICLR 2024 Roleplay-doh: Enabling Domain-Experts to Create LLM-simulated Patients via Eliciting and Adhering to Principles EMNLP 2024 Supervised Pretraining Can Learn In-Context Reinforcement Learning NIPS 2023 Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets NIPS 2023 Model-Based Offline Reinforcement Learning with Local Misspecification AAAI 2023 Experiment Planning with Function Approximation NIPS 2023 Proportional Response: Contextual Bandits for Simple and Cumulative Regret Minimization NIPS 2023 Constraint Sampling Reinforcement Learning: Incorporating Expertise for Faster Learning AAAI 2022 Offline policy optimization with eligible actions UAI 2022 Factored DRO: Factored Distributionally Robust Policies for Contextual Bandits NIPS 2022 Off-Policy Evaluation for Action-Dependent Non-stationary Environments NIPS 2022 Data-Efficient Pipeline for Offline Reinforcement Learning with Limited Data NIPS 2022 Oracle Inequalities for Model Selection in Offline Reinforcement Learning NIPS 2022 Giving Feedback on Interactive Student Programs with Meta-Exploration NIPS 2022 Online Model Selection for Reinforcement Learning with Function Approximation AISTATS 2021 Power Constrained Bandits MLHC 2021 Play to Grade: Testing Coding Games as Classifying Markov Decision Process NIPS 2021 Provable Benefits of Actor-Critic Methods for Offline Reinforcement Learning NIPS 2021 Reinforcement Learning with State Observation Costs in Action-Contingent Noiselessly Observable Markov Decision Processes NIPS 2021 Design of Experiments for Stochastic Contextual Linear Bandits NIPS 2021 Universal Off-Policy Evaluation NIPS 2021 Frequentist Regret Bounds for Randomized Least-Squares Value Iteration AISTATS 2020 Towards the Systematic Reporting of the Energy and Carbon Footprints of Machine Learning JMLR 2020 Learning Near Optimal Policies with Low Inherent Bellman Error ICML 2020 Understanding the Curse of Horizon in Off-Policy Evaluation via Conditional Importance Sampling ICML 2020 Provably Good Batch Off-Policy Reinforcement Learning Without Great Exploration NIPS 2020 Provably Efficient Reward-Agnostic Navigation with Linear Value Iteration NIPS 2020 Off-policy Policy Evaluation For Sequential Decisions Under Unobserved Confounding NIPS 2020 Being Optimistic to Be Conservative: Quickly Learning a CVaR Policy AAAI 2020 Interpretable Off-Policy Evaluation in Reinforcement Learning by Highlighting Influential Transitions ICML 2020 Sublinear Optimal Policy Value Estimation in Contextual Bandits AISTATS 2020 Offline Contextual Bandits with High Probability Fairness Guarantees NIPS 2019 Limiting Extrapolation in Linear Approximate Value Iteration NIPS 2019 Almost Horizon-Free Structure-Aware Best Policy Identification with a Generative Model NIPS 2019 Learning Procedural Abstractions and Evaluating Discrete Latent Temporal Structure ICLR 2019 Policy Certificates: Towards Accountable Reinforcement Learning ICML 2019 Combining parametric and nonparametric models for off-policy evaluation ICML 2019 Separating value functions across time-scales ICML 2019 Tighter Problem-Dependent Regret Bounds in Reinforcement Learning without Domain Knowledge using Value Function Bounds ICML 2019 Fake It Till You Make It: Learning-Compatible Performance Support UAI 2019 Off-Policy Policy Gradient with Stationary Distribution Correction UAI 2019 Problem Dependent Reinforcement Learning Bounds Which Can Identify Bandit Structure in MDPs ICML 2018 Representation Balancing MDPs for Off-policy Policy Evaluation NIPS 2018 Importance Sampling for Fair Policy Selection IJCAI 2018 Decoupling Gradient-Like Learning Rules from Representations ICML 2018 Unifying PAC and Regret: Uniform PAC Bounds for Episodic Reinforcement Learning NIPS 2017 Sample Efficient Policy Search for Optimal Stopping Domains IJCAI 2017 Using Options and Covariance Testing for Long Horizon Off-Policy Policy Evaluation NIPS 2017 Regret Minimization in MDPs with Options without Prior Knowledge NIPS 2017 Trading off Rewards and Errors in Multi-Armed Bandits AISTATS 2017 Questimator: Generating Knowledge Assessments for Arbitrary Topics IJCAI 2016 Energetic Natural Gradient Descent ICML 2016 A PAC RL Algorithm for Episodic POMDPs AISTATS 2016 Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning ICML 2016 Efficient Bayesian Clustering for Reinforcement Learning IJCAI 2016 Latent Contextual Bandits and their Application to Personalized Recommendations for New Users IJCAI 2016 Sample Complexity of Episodic Fixed-Horizon Reinforcement Learning NIPS 2015 PAC-inspired Option Discovery in Lifelong Reinforcement Learning ICML 2014 Online Stochastic Optimization under Correlated Bandit Feedback ICML 2014 Sequential Transfer in Multi-armed Bandit with Finite Set of Models NIPS 2013 Provably Efficient Learning with Typed Parametric Models JMLR 2009