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 Romain Laroche

Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch


Nov 04, 2021
Shangtong Zhang, Remi Tachet, Romain Laroche


  Access Paper or Ask Questions

Batched Bandits with Crowd Externalities


Sep 29, 2021
Romain Laroche, Othmane Safsafi, Raphael Feraud, Nicolas Broutin

* 31 pages 

  Access Paper or Ask Questions

Dr Jekyll and Mr Hyde: the Strange Case of Off-Policy Policy Updates


Sep 29, 2021
Romain Laroche, Remi Tachet

* accepted to NeurIPS as a poster 

  Access Paper or Ask Questions

The Emergence of the Shape Bias Results from Communicative Efficiency


Sep 15, 2021
Eva Portelance, Michael C. Frank, Dan Jurafsky, Alessandro Sordoni, Romain Laroche

* Accepted at CoNLL 2021 

  Access Paper or Ask Questions

Multi-Objective SPIBB: Seldonian Offline Policy Improvement with Safety Constraints in Finite MDPs


May 31, 2021
Harsh Satija, Philip S. Thomas, Joelle Pineau, Romain Laroche


  Access Paper or Ask Questions

A Deeper Look at Discounting Mismatch in Actor-Critic Algorithms


Oct 02, 2020
Shangtong Zhang, Romain Laroche, Harm van Seijen, Shimon Whiteson, Remi Tachet des Combes


  Access Paper or Ask Questions

Reinforcement Learning Framework for Deep Brain Stimulation Study


Feb 22, 2020
Dmitrii Krylov, Remi Tachet, Romain Laroche, Michael Rosenblum, Dmitry V. Dylov

* 7 pages + 1 references, 7 figures. arXiv admin note: text overlap with arXiv:1909.12154 

  Access Paper or Ask Questions

Learning Dynamic Knowledge Graphs to Generalize on Text-Based Games


Feb 21, 2020
Ashutosh Adhikari, Xingdi Yuan, Marc-Alexandre Côté, Mikuláš Zelinka, Marc-Antoine Rondeau, Romain Laroche, Pascal Poupart, Jian Tang, Adam Trischler, William L. Hamilton


  Access Paper or Ask Questions

Building Dynamic Knowledge Graphs from Text-based Games


Oct 22, 2019
Mikulas Zelinka, Xingdi Yuan, Marc-Alexandre Cote, Romain Laroche, Adam Trischler

* NeurIPS 2019, Graph Representation Learning(GRL) Workshop 

  Access Paper or Ask Questions

Safe Policy Improvement with an Estimated Baseline Policy


Sep 11, 2019
Thiago D. Simão, Romain Laroche, Rémi Tachet des Combes


  Access Paper or Ask Questions

Safe Policy Improvement with Soft Baseline Bootstrapping


Jul 11, 2019
Kimia Nadjahi, Romain Laroche, Rémi Tachet des Combes

* Accepted paper at ECML-PKDD2019 

  Access Paper or Ask Questions

Scaling up budgeted reinforcement learning


Mar 06, 2019
Nicolas Carrara, Edouard Leurent, Romain Laroche, Tanguy Urvoy, Odalric-Ambrym Maillard, Olivier Pietquin

* N.Carrara and E.Leurent have equally contributed. The source code, videos and additional details for all experiments are available at https://scaling-up-brl.github.io 

  Access Paper or Ask Questions

Decentralized Exploration in Multi-Armed Bandits


Dec 10, 2018
Raphaël Féraud, Réda Alami, Romain Laroche


  Access Paper or Ask Questions

Counting to Explore and Generalize in Text-based Games


Jun 29, 2018
Xingdi Yuan, Marc-Alexandre Côté, Alessandro Sordoni, Romain Laroche, Remi Tachet des Combes, Matthew Hausknecht, Adam Trischler


  Access Paper or Ask Questions

Safe Policy Improvement with Baseline Bootstrapping


Jun 14, 2018
Romain Laroche, Paul Trichelair

* 8+2+11 pages 

  Access Paper or Ask Questions

Hybrid Reward Architecture for Reinforcement Learning


Nov 28, 2017
Harm van Seijen, Mehdi Fatemi, Joshua Romoff, Romain Laroche, Tavian Barnes, Jeffrey Tsang


  Access Paper or Ask Questions

Reinforcement Learning Algorithm Selection


Nov 14, 2017
Romain Laroche, Raphael Feraud


  Access Paper or Ask Questions

Multi-Advisor Reinforcement Learning


Nov 14, 2017
Romain Laroche, Mehdi Fatemi, Joshua Romoff, Harm van Seijen

* Submitted at ICLR2018 

  Access Paper or Ask Questions

The Complex Negotiation Dialogue Game


Jul 05, 2017
Romain Laroche

* Position paper for Sigdial/Semdial 2017 special session on negotiation dialogue 

  Access Paper or Ask Questions

Separation of Concerns in Reinforcement Learning


Mar 28, 2017
Harm van Seijen, Mehdi Fatemi, Joshua Romoff, Romain Laroche


  Access Paper or Ask Questions