← Authors

Aldo Pacchiano

58 papers · 2017–2025 · 10 conferences · across top CS/AI conferences

Achievements

🐣 Hot Topic Early Bird 🌍 Conference Polyglot (10) 🌈 Renaissance Researcher (5) 🐝 Cross-Pollinator (10) πŸŒ‰ Interdisciplinary Bridge πŸ—ΊοΈ Taxonomy Completionist (18) 🧭 Keyword Pioneer πŸƒ Academic Marathon (8) 🀝 Dynamic Duo (12) πŸ‘‘ Triple Crown πŸ† Grand Slam πŸ”¬ Deep Specialist (14) πŸ† Keyword Champion πŸ”₯ Unstoppable (9) πŸš€ Conference Pioneer ⚑ Prolific Year (12) πŸ“ˆ Trend Setter πŸ’Ž Century Club (58) πŸ—ƒοΈ Keyword Collector (54)

Conferences

NIPS (19) ICML (14) AISTATS (12) ICLR (6) UAI (2) AAAI (1) ALT (1) COLT (1) CORL (1) JMLR (1)

Top co-authors

Jack Parker-Holder (12) Krzysztof Choromanski (8) Jonathan Lee (6) Peter Bartlett (6) Michael Jordan (6) Yunhao Tang (6) Heinrich Jiang (4) Michael I. Jordan (4) Vikas Sindhwani (3) Philip Ball (3)

Keywords

regret bound (16) reinforcement learning (14) model selection (7) multi-armed bandit (7) online learning (6) contextual bandit (5) policy optimization (4) continuous control (3) linear bandit (3) blackbox optimization (3) function approximation (3) sample complexity (3) linear programming relaxation (3) wasserstein distance (2) sample efficiency (2) gradient descent (2) stochastic gradient descent (2) deep reinforcement learning (2) markov decision process (2) active learning (2)

Papers

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