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

 Add to Chrome

 Add to Firefox

CatalyzeX Code Finder - Browser extension linking code for ML papers across the web! | Product Hunt Embed
Scalable Reinforcement Learning Policies for Multi-Agent Control

Nov 16, 2020
Christopher D. Hsu, Heejin Jeong, George J. Pappas, Pratik Chaudhari

* 8 pages, 10 figures, submitted to RA-L with ICRA option 

  Access Paper or Ask Questions

An Information-Geometric Distance on the Space of Tasks

Nov 01, 2020
Yansong Gao, Pratik Chaudhari


  Access Paper or Ask Questions

MIDAS: Multi-agent Interaction-aware Decision-making with Adaptive Strategies for Urban Autonomous Navigation

Aug 17, 2020
Xiaoyi Chen, Pratik Chaudhari

* Code available at https://github.com/sherrychen1120/MIDAS 

  Access Paper or Ask Questions

Proximal Deterministic Policy Gradient

Aug 03, 2020
Marco Maggipinto, Gian Antonio Susto, Pratik Chaudhari


  Access Paper or Ask Questions

DDPG++: Striving for Simplicity in Continuous-control Off-Policy Reinforcement Learning

Jun 26, 2020
Rasool Fakoor, Pratik Chaudhari, Alexander J. Smola


  Access Paper or Ask Questions

Fast, Accurate, and Simple Models for Tabular Data via Augmented Distillation

Jun 25, 2020
Rasool Fakoor, Jonas Mueller, Nick Erickson, Pratik Chaudhari, Alexander J. Smola


  Access Paper or Ask Questions

BayesRace: Learning to race autonomously using prior experience

May 10, 2020
Achin Jain, Pratik Chaudhari, Manfred Morari


  Access Paper or Ask Questions

TraDE: Transformers for Density Estimation

Apr 06, 2020
Rasool Fakoor, Pratik Chaudhari, Jonas Mueller, Alexander J. Smola


  Access Paper or Ask Questions

A Free-Energy Principle for Representation Learning

Feb 27, 2020
Yansong Gao, Pratik Chaudhari

* 21 pages, 14 figures 

  Access Paper or Ask Questions

Rethinking the Hyperparameters for Fine-tuning

Feb 19, 2020
Hao Li, Pratik Chaudhari, Hao Yang, Michael Lam, Avinash Ravichandran, Rahul Bhotika, Stefano Soatto

* Published as a conference paper at ICLR 2020 

  Access Paper or Ask Questions

Directional Adversarial Training for Cost Sensitive Deep Learning Classification Applications

Oct 08, 2019
Matteo Terzi, Gian Antonio Susto, Pratik Chaudhari


  Access Paper or Ask Questions

Meta-Q-Learning

Sep 30, 2019
Rasool Fakoor, Pratik Chaudhari, Stefano Soatto, Alexander J. Smola


  Access Paper or Ask Questions

A Baseline for Few-Shot Image Classification

Sep 06, 2019
Guneet S. Dhillon, Pratik Chaudhari, Avinash Ravichandran, Stefano Soatto


  Access Paper or Ask Questions

P3O: Policy-on Policy-off Policy Optimization

May 05, 2019
Rasool Fakoor, Pratik Chaudhari, Alexander J. Smola


  Access Paper or Ask Questions

Stochastic gradient descent performs variational inference, converges to limit cycles for deep networks

Jan 16, 2018
Pratik Chaudhari, Stefano Soatto


  Access Paper or Ask Questions

Parle: parallelizing stochastic gradient descent

Sep 10, 2017
Pratik Chaudhari, Carlo Baldassi, Riccardo Zecchina, Stefano Soatto, Ameet Talwalkar, Adam Oberman


  Access Paper or Ask Questions

On the energy landscape of deep networks

Apr 21, 2017
Pratik Chaudhari, Stefano Soatto


  Access Paper or Ask Questions

Entropy-SGD: Biasing Gradient Descent Into Wide Valleys

Apr 21, 2017
Pratik Chaudhari, Anna Choromanska, Stefano Soatto, Yann LeCun, Carlo Baldassi, Christian Borgs, Jennifer Chayes, Levent Sagun, Riccardo Zecchina

* ICLR '17 

  Access Paper or Ask Questions

Incremental Sampling-based Algorithm for Minimum-violation Motion Planning

Nov 06, 2013
Luis I. Reyes Castro, Pratik Chaudhari, Jana Tumova, Sertac Karaman, Emilio Frazzoli, Daniela Rus

* 8 pages, final version submitted to CDC '13 

  Access Paper or Ask Questions