Aldo Pacchiano

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...
01/19/2021 ∙ by Xingyou Song, et al. ∙ 16 ∙ share

read it
Fairness with Continuous Optimal Transport

Whilst optimal transport (OT) is increasingly being recognized as a powe...
01/06/2021 ∙ by Silvia Chiappa, et al. ∙ 0 ∙ share

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

We propose a simple model selection approach for algorithms in stochasti...
12/24/2020 ∙ by Aldo Pacchiano, et al. ∙ 0 ∙ share

read it
Online Model Selection for Reinforcement Learning with Function Approximation

Deep reinforcement learning has achieved impressive successes yet often ...
11/19/2020 ∙ by Jonathan N. Lee, et al. ∙ 0 ∙ share

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

Over the last decade, a single algorithm has changed many facets of our ...
11/12/2020 ∙ by Jack Parker-Holder, et al. ∙ 11 ∙ share

read it
Accelerated Message Passing for Entropy-Regularized MAP Inference

Maximum a posteriori (MAP) inference in discrete-valued Markov random fi...
07/01/2020 ∙ by Jonathan N. Lee, et al. ∙ 11 ∙ share

read it
On Optimism in Model-Based Reinforcement Learning

The principle of optimism in the face of uncertainty is prevalent throug...
06/21/2020 ∙ by Aldo Pacchiano, et al. ∙ 0 ∙ share

read it
Stochastic Bandits with Linear Constraints

We study a constrained contextual linear bandit setting, where the goal ...
06/17/2020 ∙ by Aldo Pacchiano, et al. ∙ 0 ∙ share

read it
Regret Balancing for Bandit and RL Model Selection

We consider model selection in stochastic bandit and reinforcement learn...
06/09/2020 ∙ by Yasin Abbasi-Yadkori, et al. ∙ 9 ∙ share

read it
Learning the Truth From Only One Side of the Story

Learning under one-sided feedback (i.e., where examples arrive in an onl...
06/08/2020 ∙ by Heinrich Jiang, et al. ∙ 6 ∙ share

read it
Stochastic Flows and Geometric Optimization on the Orthogonal Group

We present a new class of stochastic, geometrically-driven optimization ...
03/30/2020 ∙ by Krzysztof Choromanski, et al. ∙ 2 ∙ share

read it
Robustness Guarantees for Mode Estimation with an Application to Bandits

Mode estimation is a classical problem in statistics with a wide range o...
03/05/2020 ∙ by Aldo Pacchiano, et al. ∙ 5 ∙ share

read it
Model Selection in Contextual Stochastic Bandit Problems

We study model selection in stochastic bandit problems. Our approach rel...
03/03/2020 ∙ by Aldo Pacchiano, et al. ∙ 0 ∙ share

read it
On Thompson Sampling with Langevin Algorithms

Thompson sampling is a methodology for multi-armed bandit problems that ...
02/23/2020 ∙ by Eric Mazumdar, et al. ∙ 9 ∙ share

read it
Ready Policy One: World Building Through Active Learning

Model-Based Reinforcement Learning (MBRL) offers a promising direction f...
02/07/2020 ∙ by Philip Ball, et al. ∙ 10 ∙ share

read it
Effective Diversity in Population-Based Reinforcement Learning

Maintaining a population of solutions has been shown to increase explora...
02/03/2020 ∙ by Jack Parker-Holder, et al. ∙ 18 ∙ share

read it
ES-MAML: Simple Hessian-Free Meta Learning

We introduce ES-MAML, a new framework for solving the model agnostic met...
09/25/2019 ∙ by Xingyou Song, et al. ∙ 16 ∙ share

read it
Wasserstein Fair Classification

We propose an approach to fair classification that enforces independence...
07/28/2019 ∙ by Ray Jiang, et al. ∙ 7 ∙ share

read it
Reinforcement Learning with Chromatic Networks

We present a new algorithm for finding compact neural networks encoding ...
07/10/2019 ∙ by Xingyou Song, et al. ∙ 6 ∙ share

read it
Approximate Sherali-Adams Relaxations for MAP Inference via Entropy Regularization

Maximum a posteriori (MAP) inference is a fundamental computational para...
07/02/2019 ∙ by Jonathan N. Lee, et al. ∙ 3 ∙ share

read it
Wasserstein Reinforcement Learning

We propose behavior-driven optimization via Wasserstein distances (WDs) ...
06/11/2019 ∙ by Aldo Pacchiano, et al. ∙ 1 ∙ share

read it
Structured Monte Carlo Sampling for Nonisotropic Distributions via Determinantal Point Processes

We propose a new class of structured methods for Monte Carlo (MC) sampli...
05/29/2019 ∙ by Krzysztof Choromanski, et al. ∙ 8 ∙ share

read it
Adaptive Sample-Efficient Blackbox Optimization via ES-active Subspaces

We present a new algorithm ASEBO for conducting optimization of high-dim...
03/07/2019 ∙ by Krzysztof Choromanski, et al. ∙ 12 ∙ share

read it
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...
03/07/2019 ∙ by Krzysztof Choromanski, et al. ∙ 12 ∙ share

read it
Gen-Oja: A Simple and Efficient Algorithm for Streaming Generalized Eigenvector Computation

In this paper, we study the problems of principal Generalized Eigenvecto...
11/20/2018 ∙ by Kush Bhatia, et al. ∙ 0 ∙ share

read it
Online learning with kernel losses

We present a generalization of the adversarial linear bandits framework,...
02/27/2018 ∙ by Aldo Pacchiano, et al. ∙ 0 ∙ share

read it
A note on reinforcement learning with Wasserstein distance regularisation, with applications to multipolicy learning

In this note we describe an application of Wasserstein distance to Reinf...
02/12/2018 ∙ by Mohammed Amin Abdullah, et al. ∙ 0 ∙ share

read it

Aldo Pacchiano

Featured Co-authors

Michael I. Jordan

Csaba Szepesvari

Stephen Roberts

Mohammad Ghavamzadeh

Emma Brunskill

Peter L. Bartlett

Tor Lattimore

Yuan Gao

Krzysztof Choromanski

Adrian Weller

Vikas Sindhwani

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

Fairness with Continuous Optimal Transport

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

Online Model Selection for Reinforcement Learning with Function Approximation

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

Accelerated Message Passing for Entropy-Regularized MAP Inference

On Optimism in Model-Based Reinforcement Learning

Stochastic Bandits with Linear Constraints

Regret Balancing for Bandit and RL Model Selection

Learning the Truth From Only One Side of the Story

Stochastic Flows and Geometric Optimization on the Orthogonal Group

Robustness Guarantees for Mode Estimation with an Application to Bandits

Model Selection in Contextual Stochastic Bandit Problems

On Thompson Sampling with Langevin Algorithms

Ready Policy One: World Building Through Active Learning

Effective Diversity in Population-Based Reinforcement Learning

ES-MAML: Simple Hessian-Free Meta Learning

Wasserstein Fair Classification

Reinforcement Learning with Chromatic Networks

Approximate Sherali-Adams Relaxations for MAP Inference via Entropy Regularization

Wasserstein Reinforcement Learning

Structured Monte Carlo Sampling for Nonisotropic Distributions via Determinantal Point Processes

Adaptive Sample-Efficient Blackbox Optimization via ES-active Subspaces

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

Gen-Oja: A Simple and Efficient Algorithm for Streaming Generalized Eigenvector Computation

Online learning with kernel losses

A note on reinforcement learning with Wasserstein distance regularisation, with applications to multipolicy learning