Aldo Pacchiano

19

Papers

8

Total Citations

Papers (19)

Second Order Bounds for Contextual Bandits with Function Approximation

Multiple-policy Evaluation via Density Estimation

Principled Fine-tuning of LLMs from User-Edits: A Medley of Preference, Supervision, and Reward

NeurIPS 2025arXiv

Provable Interactive Learning with Hindsight Instruction Feedback

Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian

NeurIPS 2020arXiv

Model Selection in Contextual Stochastic Bandit Problems

NeurIPS 2020arXiv

Effective Diversity in Population Based Reinforcement Learning

NeurIPS 2020arXiv

Near Optimal Policy Optimization via REPS

NeurIPS 2021arXiv

On the Theory of Reinforcement Learning with Once-per-Episode Feedback

NeurIPS 2021arXiv

Neural Pseudo-Label Optimism for the Bank Loan Problem

NeurIPS 2021arXiv

Tactical Optimism and Pessimism for Deep Reinforcement Learning

NeurIPS 2021arXiv

Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection

NeurIPS 2021arXiv

Best of Both Worlds Model Selection

NeurIPS 2022arXiv

Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity

NeurIPS 2022arXiv

Learning General World Models in a Handful of Reward-Free Deployments

NeurIPS 2022arXiv

Experiment Planning with Function Approximation

NeurIPS 2023arXiv

Anytime Model Selection in Linear Bandits

NeurIPS 2023arXiv

Supervised Pretraining Can Learn In-Context Reinforcement Learning

NeurIPS 2023arXiv

A Unified Model and Dimension for Interactive Estimation

NeurIPS 2023arXiv