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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Masked Imitation Learning: Discovering Environment-Invariant Modalities in Multimodal Demonstrations


Sep 16, 2022
Yilun Hao, Ruinan Wang, Zhangjie Cao, Zihan Wang, Yuchen Cui, Dorsa Sadigh

* 13 pages 

   Access Paper or Ask Questions

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

Training and Inference on Any-Order Autoregressive Models the Right Way


May 26, 2022
Andy Shih, Dorsa Sadigh, Stefano Ermon


   Access Paper or Ask Questions

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

Leveraging Smooth Attention Prior for Multi-Agent Trajectory Prediction


Mar 19, 2022
Zhangjie Cao, Erdem Bıyık, Guy Rosman, Dorsa Sadigh

* ICRA 2022 
* 8 pages 

   Access Paper or Ask Questions

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

PLATO: Predicting Latent Affordances Through Object-Centric Play


Mar 10, 2022
Suneel Belkhale, Dorsa Sadigh


   Access Paper or Ask Questions

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

Weakly Supervised Correspondence Learning


Mar 07, 2022
Zihan Wang, Zhangjie Cao, Yilun Hao, Dorsa Sadigh


   Access Paper or Ask Questions

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

Learning from Imperfect Demonstrations via Adversarial Confidence Transfer


Feb 07, 2022
Zhangjie Cao, Zihan Wang, Dorsa Sadigh


   Access Paper or Ask Questions

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

Imitation Learning by Estimating Expertise of Demonstrators


Feb 02, 2022
Mark Beliaev, Andy Shih, Stefano Ermon, Dorsa Sadigh, Ramtin Pedarsani

* 15 pages 

   Access Paper or Ask Questions

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

Conditional Imitation Learning for Multi-Agent Games


Jan 05, 2022
Andy Shih, Stefano Ermon, Dorsa Sadigh

* 17th ACM/IEEE International Conference on Human-Robot Interaction (HRI), 2022 

   Access Paper or Ask Questions

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

PantheonRL: A MARL Library for Dynamic Training Interactions


Dec 13, 2021
Bidipta Sarkar, Aditi Talati, Andy Shih, Dorsa Sadigh

* 3 pages, 3 figures. Published in Proceedings of the 36th AAAI Conference on Artificial Intelligence (Demo Track) 2022 

   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
6
7
>>