← Authors

Masatoshi Uehara

34 papers · 2019–2025 · 6 conferences · across top CS/AI conferences

Achievements

🌈 Renaissance Researcher (5) 🐝 Cross-Pollinator (9) 🐣 Hot Topic Early Bird πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer πŸ—ΊοΈ Taxonomy Completionist (32) 🌍 Conference Polyglot (6) πŸƒ Academic Marathon (6) 🀝 Dynamic Duo (15) πŸ‘‘ Triple Crown πŸ”¬ Deep Specialist (14) πŸ† Keyword Champion (2) πŸ“ˆ Trend Setter πŸ’Ž Century Club (34) ⚑ Prolific Year (7) πŸ”₯ Unstoppable (7) πŸ—ƒοΈ Keyword Collector (105)

Conferences

ICML (10) NIPS (8) ICLR (7) AISTATS (3) COLT (3) JMLR (3)

Top co-authors

Nathan Kallus (15) Wen Sun (12) Sergey Levine (6) Tommaso Biancalani (5) Yulai Zhao (4) Jason D. Lee (4) Andrew Bennett (3) Xiaojie Mao (3) Nan Jiang (3) Wenhao Zhan (3)

Keywords

off-policy evaluation (8) reinforcement learning (6) function approximation (4) causal inference (4) doubly robust (4) offline reinforcement learning (3) off-policy learning (3) importance sampling (3) partially observable markov decision process (3) unnormalized model (2) regret bound (2) noise contrastive estimation (2) policy learning (2) diffusion model (2) policy gradient (2) score matching (2) markov decision process (2) covariate shift (2) minimax optimization (2) generative model (2)

Papers

Fine-Tuning Discrete Diffusion Models via Reward Optimization with Applications to DNA and Protein Design ICLR 2025
Reward-Guided Iterative Refinement in Diffusion Models at Test-Time with Applications to Protein and DNA Design ICML 2025
Adding Conditional Control to Diffusion Models with Reinforcement Learning ICLR 2025
Localized Debiased Machine Learning: Efficient Inference on Quantile Treatment Effects and Beyond JMLR 2024
Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models NIPS 2024
Functional Graphical Models: Structure Enables Offline Data-Driven Optimization AISTATS 2024
Provable Offline Preference-Based Reinforcement Learning ICLR 2024
Provable Reward-Agnostic Preference-Based Reinforcement Learning ICLR 2024
Feedback Efficient Online Fine-Tuning of Diffusion Models ICML 2024
Inference on Strongly Identified Functionals of Weakly Identified Functions COLT 2023
Future-Dependent Value-Based Off-Policy Evaluation in POMDPs NIPS 2023
PAC Reinforcement Learning for Predictive State Representations ICLR 2023
Computationally Efficient PAC RL in POMDPs with Latent Determinism and Conditional Embeddings ICML 2023
Distributional Offline Policy Evaluation with Predictive Error Guarantees ICML 2023
Minimax Instrumental Variable Regression and $L_2$ Convergence Guarantees without Identification or Closedness COLT 2023
Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage NIPS 2023
Pessimistic Model-based Offline Reinforcement Learning under Partial Coverage ICLR 2022
Representation Learning for Online and Offline RL in Low-rank MDPs ICLR 2022
A Minimax Learning Approach to Off-Policy Evaluation in Confounded Partially Observable Markov Decision Processes ICML 2022
Provably Efficient Reinforcement Learning in Partially Observable Dynamical Systems NIPS 2022
Efficient Reinforcement Learning in Block MDPs: A Model-free Representation Learning approach ICML 2022
Optimal Off-Policy Evaluation from Multiple Logging Policies ICML 2021
Fast Rates for the Regret of Offline Reinforcement Learning COLT 2021
Information criteria for non-normalized models JMLR 2021
Mitigating Covariate Shift in Imitation Learning via Offline Data With Partial Coverage NIPS 2021
A Unified Statistically Efficient Estimation Framework for Unnormalized Models AISTATS 2020
Off-Policy Evaluation and Learning for External Validity under a Covariate Shift NIPS 2020
Double Reinforcement Learning for Efficient Off-Policy Evaluation in Markov Decision Processes JMLR 2020
Doubly Robust Off-Policy Value and Gradient Estimation for Deterministic Policies NIPS 2020
Double Reinforcement Learning for Efficient and Robust Off-Policy Evaluation ICML 2020
Statistically Efficient Off-Policy Policy Gradients ICML 2020
Minimax Weight and Q-Function Learning for Off-Policy Evaluation ICML 2020
Imputation estimators for unnormalized models with missing data AISTATS 2020
Intrinsically Efficient, Stable, and Bounded Off-Policy Evaluation for Reinforcement Learning NIPS 2019