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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training


Sep 30, 2022
Yecheng Jason Ma, Shagun Sodhani, Dinesh Jayaraman, Osbert Bastani, Vikash Kumar, Amy Zhang

Add code

* Project website: https://sites.google.com/view/vip-rl 

   Access Paper or Ask Questions

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

How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via $f$-Advantage Regression


Jun 07, 2022
Yecheng Jason Ma, Jason Yan, Dinesh Jayaraman, Osbert Bastani

Add code

* Project website: https://jasonma2016.github.io/GoFAR/ 

   Access Paper or Ask Questions

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

SMODICE: Versatile Offline Imitation Learning via State Occupancy Matching


Feb 04, 2022
Yecheng Jason Ma, Andrew Shen, Dinesh Jayaraman, Osbert Bastani

Add code

* Project website: https://sites.google.com/view/smodice/home 

   Access Paper or Ask Questions

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

Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning


Dec 14, 2021
Yecheng Jason Ma, Andrew Shen, Osbert Bastani, Dinesh Jayaraman

Add code

* AAAI 2022 

   Access Paper or Ask Questions

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

Safe Human-Interactive Control via Shielding


Oct 11, 2021
Jeevana Priya Inala, Yecheng Jason Ma, Osbert Bastani, Xin Zhang, Armando Solar-Lezama

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

State Relevance for Off-Policy Evaluation


Sep 13, 2021
Simon P. Shen, Yecheng Jason Ma, Omer Gottesman, Finale Doshi-Velez

Add code

* Proceedings of the 38th International Conference on Machine Learning, PMLR 139:9537-9546, 2021 
* ICML 2021 

   Access Paper or Ask Questions

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

Conservative Offline Distributional Reinforcement Learning


Jul 12, 2021
Yecheng Jason Ma, Dinesh Jayaraman, Osbert Bastani

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

Diverse Sampling for Normalizing Flow Based Trajectory Forecasting


Nov 30, 2020
Yecheng Jason Ma, Jeevana Priya Inala, Dinesh Jayaraman, Osbert Bastani

Add code

* Technical report, 18 pages 

   Access Paper or Ask Questions

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