Aldo Pacchiano

research

∙ 08/15/2023

Unbiased Decisions Reduce Regret: Adversarial Domain Adaptation for the Bank Loan Problem

In many real world settings binary classification decisions are made bas...

0 Elena Gal, et al. ∙

research

∙ 07/24/2023

Anytime Model Selection in Linear Bandits

Model selection in the context of bandit optimization is a challenging p...

0 Parnian Kassraie, et al. ∙

research

∙ 06/26/2023

Supervised Pretraining Can Learn In-Context Reinforcement Learning

Large transformer models trained on diverse datasets have shown a remark...

0 Jonathan N. Lee, et al. ∙

research

∙ 06/09/2023

A Unified Model and Dimension for Interactive Estimation

We study an abstract framework for interactive learning called interacti...

0 Nataly Brukhim, et al. ∙

research

∙ 06/05/2023

Data-Driven Regret Balancing for Online Model Selection in Bandits

We consider model selection for sequential decision making in stochastic...

0 Aldo Pacchiano, et al. ∙

research

∙ 06/01/2023

Improving Offline RL by Blending Heuristics

We propose Heuristic Blending (HUBL), a simple performance-improving tec...

0 Sinong Geng, et al. ∙

research

∙ 02/19/2023

Estimating Optimal Policy Value in General Linear Contextual Bandits

In many bandit problems, the maximal reward achievable by a policy is of...

0 Jonathan N. Lee, et al. ∙

research

∙ 11/26/2022

Transfer RL via the Undo Maps Formalism

Transferring knowledge across domains is one of the most fundamental pro...

0 Abhi Gupta, et al. ∙

research

∙ 11/09/2022

Leveraging Offline Data in Online Reinforcement Learning

Two central paradigms have emerged in the reinforcement learning (RL) co...

0 Andrew Wagenmaker, et al. ∙

research

∙ 10/23/2022

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

Building generally capable agents is a grand challenge for deep reinforc...

0 Yingchen Xu, et al. ∙

research

∙ 10/18/2022

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

Reinforcement learning provides an automated framework for learning beha...

0 Abhishek Gupta, et al. ∙

research

∙ 07/26/2022

Neural Design for Genetic Perturbation Experiments

The problem of how to genetically modify cells in order to maximize a ce...

0 Aldo Pacchiano, et al. ∙

research

∙ 06/29/2022

Best of Both Worlds Model Selection

We study the problem of model selection in bandit scenarios in the prese...

0 Aldo Pacchiano, et al. ∙

research

∙ 06/24/2022

Joint Representation Training in Sequential Tasks with Shared Structure

Classical theory in reinforcement learning (RL) predominantly focuses on...

0 Aldo Pacchiano, et al. ∙

research

∙ 05/15/2022

Online Nonsubmodular Minimization with Delayed Costs: From Full Information to Bandit Feedback

Motivated by applications to online learning in sparse estimation and Ba...

6 Tianyi Lin, et al. ∙

research

∙ 01/21/2022

Meta Learning MDPs with Linear Transition Models

We study meta-learning in Markov Decision Processes (MDP) with linear tr...

3 Robert Müller, et al. ∙

research

∙ 12/03/2021

Neural Pseudo-Label Optimism for the Bank Loan Problem

We study a class of classification problems best exemplified by the bank...

8 Aldo Pacchiano, et al. ∙

research

∙ 11/08/2021

An Instance-Dependent Analysis for the Cooperative Multi-Player Multi-Armed Bandit

We study the problem of information sharing and cooperation in Multi-Pla...

0 Aldo Pacchiano, et al. ∙

research

∙ 11/04/2021

Towards an Understanding of Default Policies in Multitask Policy Optimization

Much of the recent success of deep reinforcement learning has been drive...

0 Ted Moskovitz, et al. ∙

research

∙ 10/27/2021

Reinforcement Learning in Linear MDPs: Constant Regret and Representation Selection

We study the role of the representation of state-action value functions ...

12 Matteo Papini, et al. ∙

research

∙ 06/15/2021

Sample Efficient Reinforcement Learning In Continuous State Spaces: A Perspective Beyond Linearity

Reinforcement learning (RL) is empirically successful in complex nonline...

2 Dhruv Malik, et al. ∙

research

∙ 05/29/2021

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

We study a theory of reinforcement learning (RL) in which the learner re...

11 Niladri S. Chatterji, et al. ∙

research

∙ 05/21/2021

Parallelizing Contextual Linear Bandits

Standard approaches to decision-making under uncertainty focus on sequen...

9 Jeffrey Chan, et al. ∙

research

∙ 03/17/2021

Near Optimal Policy Optimization via REPS

Since its introduction a decade ago, relative entropy policy search (REP...

0 Aldo Pacchiano, et al. ∙

research

∙ 02/08/2021

Unlocking Pixels for Reinforcement Learning via Implicit Attention

There has recently been significant interest in training reinforcement l...

1 Krzysztof Choromanski, et al. ∙

research

∙ 02/07/2021

Deep Reinforcement Learning with Dynamic Optimism

In recent years, deep off-policy actor-critic algorithms have become a d...

0 Ted Moskovitz, et al. ∙

research

∙ 01/19/2021

ES-ENAS: Combining Evolution Strategies with Neural Architecture Search at No Extra Cost for Reinforcement Learning

We introduce ES-ENAS, a simple neural architecture search (NAS) algorith...

16 Xingyou Song, et al. ∙

research

∙ 01/06/2021

Fairness with Continuous Optimal Transport

Whilst optimal transport (OT) is increasingly being recognized as a powe...

0 Silvia Chiappa, et al. ∙

research

∙ 12/24/2020

Regret Bound Balancing and Elimination for Model Selection in Bandits and RL

We propose a simple model selection approach for algorithms in stochasti...

0 Aldo Pacchiano, et al. ∙

research

∙ 11/19/2020

Online Model Selection for Reinforcement Learning with Function Approximation

Deep reinforcement learning has achieved impressive successes yet often ...

0 Jonathan N. Lee, et al. ∙

research

∙ 11/12/2020

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

Over the last decade, a single algorithm has changed many facets of our ...

11 Jack Parker-Holder, et al. ∙

research

∙ 07/01/2020

Accelerated Message Passing for Entropy-Regularized MAP Inference

Maximum a posteriori (MAP) inference in discrete-valued Markov random fi...

11 Jonathan N. Lee, et al. ∙

research

∙ 06/21/2020

On Optimism in Model-Based Reinforcement Learning

The principle of optimism in the face of uncertainty is prevalent throug...

0 Aldo Pacchiano, et al. ∙

research

∙ 06/17/2020

Stochastic Bandits with Linear Constraints

We study a constrained contextual linear bandit setting, where the goal ...

0 Aldo Pacchiano, et al. ∙

research

∙ 06/09/2020

Regret Balancing for Bandit and RL Model Selection

We consider model selection in stochastic bandit and reinforcement learn...

9 Yasin Abbasi-Yadkori, et al. ∙

research

∙ 06/08/2020

Learning the Truth From Only One Side of the Story

Learning under one-sided feedback (i.e., where examples arrive in an onl...

6 Heinrich Jiang, et al. ∙

research

∙ 03/30/2020

Stochastic Flows and Geometric Optimization on the Orthogonal Group

We present a new class of stochastic, geometrically-driven optimization ...

2 Krzysztof Choromanski, et al. ∙

research

∙ 03/05/2020

Robustness Guarantees for Mode Estimation with an Application to Bandits

Mode estimation is a classical problem in statistics with a wide range o...

5 Aldo Pacchiano, et al. ∙

research

∙ 03/03/2020

Model Selection in Contextual Stochastic Bandit Problems

We study model selection in stochastic bandit problems. Our approach rel...

0 Aldo Pacchiano, et al. ∙

research

∙ 02/23/2020

On Thompson Sampling with Langevin Algorithms

Thompson sampling is a methodology for multi-armed bandit problems that ...

9 Eric Mazumdar, et al. ∙

research

∙ 02/07/2020

Ready Policy One: World Building Through Active Learning

Model-Based Reinforcement Learning (MBRL) offers a promising direction f...

10 Philip Ball, et al. ∙

research

∙ 02/03/2020

Effective Diversity in Population-Based Reinforcement Learning

Maintaining a population of solutions has been shown to increase explora...

18 Jack Parker-Holder, et al. ∙

research

∙ 09/25/2019

ES-MAML: Simple Hessian-Free Meta Learning

We introduce ES-MAML, a new framework for solving the model agnostic met...

16 Xingyou Song, et al. ∙

research

∙ 07/28/2019

Wasserstein Fair Classification

We propose an approach to fair classification that enforces independence...

7 Ray Jiang, et al. ∙

research

∙ 07/10/2019

Reinforcement Learning with Chromatic Networks

We present a new algorithm for finding compact neural networks encoding ...

6 Xingyou Song, et al. ∙

research

∙ 07/02/2019

Approximate Sherali-Adams Relaxations for MAP Inference via Entropy Regularization

Maximum a posteriori (MAP) inference is a fundamental computational para...

3 Jonathan N. Lee, et al. ∙

research

∙ 06/11/2019

Wasserstein Reinforcement Learning

We propose behavior-driven optimization via Wasserstein distances (WDs) ...

1 Aldo Pacchiano, et al. ∙

research

∙ 05/29/2019

Structured Monte Carlo Sampling for Nonisotropic Distributions via Determinantal Point Processes

We propose a new class of structured methods for Monte Carlo (MC) sampli...

8 Krzysztof Choromanski, et al. ∙

research

∙ 03/07/2019

Adaptive Sample-Efficient Blackbox Optimization via ES-active Subspaces

We present a new algorithm ASEBO for conducting optimization of high-dim...

12 Krzysztof Choromanski, et al. ∙

research

∙ 03/07/2019

When random search is not enough: Sample-Efficient and Noise-Robust Blackbox Optimization of RL Policies

Interest in derivative-free optimization (DFO) and "evolutionary strateg...

12 Krzysztof Choromanski, et al. ∙

Aldo Pacchiano

Featured Co-authors