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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Leveraging the Third Dimension in Contrastive Learning


Jan 27, 2023
Sumukh Aithal, Anirudh Goyal, Alex Lamb, Yoshua Bengio, Michael Mozer

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Representation Learning in Deep RL via Discrete Information Bottleneck


Dec 28, 2022
Riashat Islam, Hongyu Zang, Manan Tomar, Aniket Didolkar, Md Mofijul Islam, Samin Yeasar Arnob, Tariq Iqbal, Xin Li, Anirudh Goyal, Nicolas Heess, Alex Lamb

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Towards Data-Driven Offline Simulations for Online Reinforcement Learning


Nov 14, 2022
Shengpu Tang, Felipe Vieira Frujeri, Dipendra Misra, Alex Lamb, John Langford, Paul Mineiro, Sebastian Kochman

Add code

* Presented at the 3rd Offline Reinforcement Learning Workshop at NeurIPS 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Neural Active Learning on Heteroskedastic Distributions


Nov 02, 2022
Savya Khosla, Chew Kin Whye, Jordan T. Ash, Cyril Zhang, Kenji Kawaguchi, Alex Lamb

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Discrete Factorial Representations as an Abstraction for Goal Conditioned Reinforcement Learning


Nov 01, 2022
Riashat Islam, Hongyu Zang, Anirudh Goyal, Alex Lamb, Kenji Kawaguchi, Xin Li, Romain Laroche, Yoshua Bengio, Remi Tachet Des Combes

Add code

* Neurips 2022 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information


Oct 31, 2022
Riashat Islam, Manan Tomar, Alex Lamb, Yonathan Efroni, Hongyu Zang, Aniket Didolkar, Dipendra Misra, Xin Li, Harm van Seijen, Remi Tachet des Combes, John Langford

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

CNT (Conditioning on Noisy Targets): A new Algorithm for Leveraging Top-Down Feedback


Oct 18, 2022
Alexia Jolicoeur-Martineau, Alex Lamb, Vikas Verma, Aniket Didolkar

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Guaranteed Discovery of Controllable Latent States with Multi-Step Inverse Models


Jul 17, 2022
Alex Lamb, Riashat Islam, Yonathan Efroni, Aniket Didolkar, Dipendra Misra, Dylan Foster, Lekan Molu, Rajan Chari, Akshay Krishnamurthy, John Langford

Add code

* Project Website: https://controllable-latent-state.github.io/ 

   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Temporal Latent Bottleneck: Synthesis of Fast and Slow Processing Mechanisms in Sequence Learning


May 30, 2022
Aniket Didolkar, Kshitij Gupta, Anirudh Goyal, Alex Lamb, Nan Rosemary Ke, Yoshua Bengio

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email

Adaptive Discrete Communication Bottlenecks with Dynamic Vector Quantization


Feb 02, 2022
Dianbo Liu, Alex Lamb, Xu Ji, Pascal Notsawo, Mike Mozer, Yoshua Bengio, Kenji Kawaguchi

Add code


   Access Paper or Ask Questions

  • Share via Twitter
  • Share via Facebook
  • Share via LinkedIn
  • Share via Whatsapp
  • Share via Messenger
  • Share via Email
1
2
3
4
5
>>