Aldo Pacchiano

Adaptive Exploration for Multi-Reward Multi-Policy Evaluation ICML 2025 A Theoretical Framework for Partially-Observed Reward States in RLHF ICLR 2025 Contextual Bandits with Stage-wise Constraints JMLR 2025 Feasible Action Search for Bandit Linear Programs via Thompson Sampling ICML 2025 Multiple-policy Evaluation via Density Estimation ICML 2025 On the Hardness of Bandit Learning COLT 2025 ORSO: Accelerating Reward Design via Online Reward Selection and Policy Optimization ICLR 2025 Pure Exploration with Feedback Graphs AISTATS 2025 Second Order Bounds for Contextual Bandits with Function Approximation ICLR 2025 Data-Driven Online Model Selection With Regret Guarantees AISTATS 2024 Improving Offline RL by Blending Heuristics ICLR 2024 Provable Interactive Learning with Hindsight Instruction Feedback ICML 2024 State-free Reinforcement Learning NeurIPS 2024 An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit ALT 2023 Anytime Model Selection in Linear Bandits NeurIPS 2023 A Unified Model and Dimension for Interactive Estimation NeurIPS 2023 Dueling RL: Reinforcement Learning with Trajectory Preferences AISTATS 2023 Experiment Planning with Function Approximation NeurIPS 2023 Leveraging Offline Data in Online Reinforcement Learning ICML 2023 Neural Design for Genetic Perturbation Experiments ICLR 2023 Supervised Pretraining Can Learn In-Context Reinforcement Learning NeurIPS 2023 Best of Both Worlds Model Selection NeurIPS 2022 Learning General World Models in a Handful of Reward-Free Deployments NeurIPS 2022 Meta Learning MDPs with linear transition models AISTATS 2022 Online Nonsubmodular Minimization with Delayed Costs: From Full Information to Bandit Feedback ICML 2022 Towards an Understanding of Default Policies in Multitask Policy Optimization AISTATS 2022 Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity NeurIPS 2022 Dynamic Balancing for Model Selection in Bandits and RL ICML 2021 Learning the Truth From Only One Side of the Story AISTATS 2021 Near Optimal Policy Optimization via REPS NeurIPS 2021 Neural Pseudo-Label Optimism for the Bank Loan Problem NeurIPS 2021 Online Model Selection for Reinforcement Learning with Function Approximation AISTATS 2021 On the Theory of Reinforcement Learning with Once-per-Episode Feedback NeurIPS 2021 Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection NeurIPS 2021 Robustness Guarantees for Mode Estimation with an Application to Bandits AAAI 2021 Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity ICML 2021 Stochastic Bandits with Linear Constraints AISTATS 2021 Tactical Optimism and Pessimism for Deep Reinforcement Learning NeurIPS 2021 Towards tractable optimism in model-based reinforcement learning UAI 2021 Accelerated Message Passing for Entropy-Regularized MAP Inference ICML 2020 Convergence Rates of Smooth Message Passing with Rounding in Entropy-Regularized MAP Inference AISTATS 2020 Effective Diversity in Population Based Reinforcement Learning NeurIPS 2020 ES-MAML: Simple Hessian-Free Meta Learning ICLR 2020 Learning to Score Behaviors for Guided Policy Optimization ICML 2020 Model Selection in Contextual Stochastic Bandit Problems NeurIPS 2020 On Approximate Thompson Sampling with Langevin Algorithms ICML 2020 Practical Nonisotropic Monte Carlo Sampling in High Dimensions via Determinantal Point Processes AISTATS 2020 Ready Policy One: World Building Through Active Learning ICML 2020 Ridge Rider: Finding Diverse Solutions by Following Eigenvectors of the Hessian NeurIPS 2020 Stochastic Flows and Geometric Optimization on the Orthogonal Group ICML 2020 From Complexity to Simplicity: Adaptive ES-Active Subspaces for Blackbox Optimization NeurIPS 2019 KAMA-NNs: Low-dimensional Rotation Based Neural Networks AISTATS 2019 Online learning with kernel losses ICML 2019 Provably Robust Blackbox Optimization for Reinforcement Learning CoRL 2019 Wasserstein Fair Classification UAI 2019 Gen-Oja: Simple & Efficient Algorithm for Streaming Generalized Eigenvector Computation NeurIPS 2018 Geometrically Coupled Monte Carlo Sampling NeurIPS 2018 Conditions beyond treewidth for tightness of higher-order LP relaxations AISTATS 2017