Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Aldo Pacchiano

Near Optimal Policy Optimization via REPS


Mar 17, 2021
Aldo Pacchiano, Jonathan Lee, Peter Bartlett, Ofir Nachum

* 8 main pages, 37 total pages 

  Access Paper or Ask Questions

Unlocking Pixels for Reinforcement Learning via Implicit Attention


Mar 04, 2021
Krzysztof Choromanski, Deepali Jain, Jack Parker-Holder, Xingyou Song, Valerii Likhosherstov, Anirban Santara, Aldo Pacchiano, Yunhao Tang, Adrian Weller


  Access Paper or Ask Questions

Deep Reinforcement Learning with Dynamic Optimism


Feb 09, 2021
Ted Moskovitz, Jack Parker-Holder, Aldo Pacchiano, Michael Arbel


  Access Paper or Ask Questions

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


Jan 19, 2021
Xingyou Song, Krzysztof Choromanski, Jack Parker-Holder, Yunhao Tang, Daiyi Peng, Deepali Jain, Wenbo Gao, Aldo Pacchiano, Tamas Sarlos, Yuxiang Yang

* 14 pages. This is an updated version of a previous submission which can be found at arXiv:1907.06511. See https://github.com/google-research/google-research/tree/master/es_enas for associated code 

  Access Paper or Ask Questions

Fairness with Continuous Optimal Transport


Jan 06, 2021
Silvia Chiappa, Aldo Pacchiano


  Access Paper or Ask Questions

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


Dec 24, 2020
Aldo Pacchiano, Christoph Dann, Claudio Gentile, Peter Bartlett

* 57 pages 

  Access Paper or Ask Questions

Online Model Selection for Reinforcement Learning with Function Approximation


Nov 19, 2020
Jonathan N. Lee, Aldo Pacchiano, Vidya Muthukumar, Weihao Kong, Emma Brunskill


  Access Paper or Ask Questions

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


Nov 12, 2020
Jack Parker-Holder, Luke Metz, Cinjon Resnick, Hengyuan Hu, Adam Lerer, Alistair Letcher, Alex Peysakhovich, Aldo Pacchiano, Jakob Foerster

* Camera-ready version, NeurIPS 2020 

  Access Paper or Ask Questions

Accelerated Message Passing for Entropy-Regularized MAP Inference


Jul 01, 2020
Jonathan N. Lee, Aldo Pacchiano, Peter Bartlett, Michael I. Jordan


  Access Paper or Ask Questions

On Optimism in Model-Based Reinforcement Learning


Jun 21, 2020
Aldo Pacchiano, Philip Ball, Jack Parker-Holder, Krzysztof Choromanski, Stephen Roberts


  Access Paper or Ask Questions

Stochastic Bandits with Linear Constraints


Jun 17, 2020
Aldo Pacchiano, Mohammad Ghavamzadeh, Peter Bartlett, Heinrich Jiang

* 9 pages 

  Access Paper or Ask Questions

Regret Balancing for Bandit and RL Model Selection


Jun 09, 2020
Yasin Abbasi-Yadkori, Aldo Pacchiano, My Phan

* Submitted to the Thirty-Fourth Annual Conference on Neural Information Processing Systems (NeurIPS 2020) 

  Access Paper or Ask Questions

Learning the Truth From Only One Side of the Story


Jun 08, 2020
Heinrich Jiang, Qijia Jiang, Aldo Pacchiano


  Access Paper or Ask Questions

Stochastic Flows and Geometric Optimization on the Orthogonal Group


Mar 30, 2020
Krzysztof Choromanski, David Cheikhi, Jared Davis, Valerii Likhosherstov, Achille Nazaret, Achraf Bahamou, Xingyou Song, Mrugank Akarte, Jack Parker-Holder, Jacob Bergquist, Yuan Gao, Aldo Pacchiano, Tamas Sarlos, Adrian Weller, Vikas Sindhwani


  Access Paper or Ask Questions

Robustness Guarantees for Mode Estimation with an Application to Bandits


Mar 05, 2020
Aldo Pacchiano, Heinrich Jiang, Michael I. Jordan

* 12 pages, 7 figures, 14 appendix pages 

  Access Paper or Ask Questions

Model Selection in Contextual Stochastic Bandit Problems


Mar 03, 2020
Aldo Pacchiano, My Phan, Yasin Abbasi-Yadkori, Anup Rao, Julian Zimmert, Tor Lattimore, Csaba Szepesvari

* 12 main pages, 2 figures, 14 appendix pages 

  Access Paper or Ask Questions

On Thompson Sampling with Langevin Algorithms


Feb 23, 2020
Eric Mazumdar, Aldo Pacchiano, Yi-an Ma, Peter L. Bartlett, Michael I. Jordan


  Access Paper or Ask Questions

Ready Policy One: World Building Through Active Learning


Feb 07, 2020
Philip Ball, Jack Parker-Holder, Aldo Pacchiano, Krzysztof Choromanski, Stephen Roberts


  Access Paper or Ask Questions

Effective Diversity in Population-Based Reinforcement Learning


Feb 03, 2020
Jack Parker-Holder, Aldo Pacchiano, Krzysztof Choromanski, Stephen Roberts


  Access Paper or Ask Questions

ES-MAML: Simple Hessian-Free Meta Learning


Oct 05, 2019
Xingyou Song, Wenbo Gao, Yuxiang Yang, Krzysztof Choromanski, Aldo Pacchiano, Yunhao Tang

* 10 main pages, 21 total pages, 21 figures 

  Access Paper or Ask Questions

Wasserstein Fair Classification


Jul 28, 2019
Ray Jiang, Aldo Pacchiano, Tom Stepleton, Heinrich Jiang, Silvia Chiappa

* Proceedings of the Thirty-Fifth Conference on Uncertainty in Artificial Intelligence, 2019 

  Access Paper or Ask Questions

Reinforcement Learning with Chromatic Networks


Jul 10, 2019
Xingyou Song, Krzysztof Choromanski, Jack Parker-Holder, Yunhao Tang, Wenbo Gao, Aldo Pacchiano, Tamas Sarlos, Deepali Jain, Yuxiang Yang

* 10 main pages, 22 total pages 

  Access Paper or Ask Questions

Approximate Sherali-Adams Relaxations for MAP Inference via Entropy Regularization


Jul 02, 2019
Jonathan N. Lee, Aldo Pacchiano, Michael I. Jordan


  Access Paper or Ask Questions

Wasserstein Reinforcement Learning


Jun 19, 2019
Aldo Pacchiano, Jack Parker-Holder, Yunhao Tang, Anna Choromanska, Krzysztof Choromanski, Michael I. Jordan


  Access Paper or Ask Questions

Structured Monte Carlo Sampling for Nonisotropic Distributions via Determinantal Point Processes


May 29, 2019
Krzysztof Choromanski, Aldo Pacchiano, Jack Parker-Holder, Yunhao Tang


  Access Paper or Ask Questions

Adaptive Sample-Efficient Blackbox Optimization via ES-active Subspaces


Mar 12, 2019
Krzysztof Choromanski, Aldo Pacchiano, Jack Parker-Holder, Yunhao Tang


  Access Paper or Ask Questions

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


Mar 07, 2019
Krzysztof Choromanski, Aldo Pacchiano, Jack Parker-Holder, Jasmine Hsu, Atil Iscen, Deepali Jain, Vikas Sindhwani


  Access Paper or Ask Questions