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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Safety-Constrained Policy Transfer with Successor Features


Nov 10, 2022
Zeyu Feng, Bowen Zhang, Jianxin Bi, Harold Soh

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

Observed Adversaries in Deep Reinforcement Learning


Oct 13, 2022
Eugene Lim, Harold Soh

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

SCALES: From Fairness Principles to Constrained Decision-Making


Sep 22, 2022
Sreejith Balakrishnan, Jianxin Bi, Harold Soh

Add code

* Accepted to the 2022 AAAI/ACM Conference on AI, Ethics, and Society (AIES '22), Updated version with additional citations, 14 pages 

   Access Paper or Ask Questions

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

MIRROR: Differentiable Deep Social Projection for Assistive Human-Robot Communication


Mar 06, 2022
Kaiqi Chen, Jeffrey Fong, Harold Soh

Add code

* 17 pages 

   Access Paper or Ask Questions

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

Deep Explicit Duration Switching Models for Time Series


Oct 26, 2021
Abdul Fatir Ansari, Konstantinos Benidis, Richard Kurle, Ali Caner Turkmen, Harold Soh, Alexander J. Smola, Yuyang Wang, Tim Januschowski

Add code

* Accepted at NeurIPS 2021 

   Access Paper or Ask Questions

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

Multi-Modal Mutual Information (MuMMI) Training for Robust Self-Supervised Deep Reinforcement Learning


Jul 06, 2021
Kaiqi Chen, Yong Lee, Harold Soh

Add code

* 10 pages, Published in ICRA 2021 

   Access Paper or Ask Questions

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

Extended Tactile Perception: Vibration Sensing through Tools and Grasped Objects


Jun 01, 2021
Tasbolat Taunyazov, Luar Shui Song, Eugene Lim, Hian Hian See, David Lee, Benjamin C. K. Tee, Harold Soh

Add code

* 9 pages, 7 figures 

   Access Paper or Ask Questions

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

Embedding Symbolic Temporal Knowledge into Deep Sequential Models


Jan 28, 2021
Yaqi Xie, Fan Zhou, Harold Soh

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

Refining Deep Generative Models via Wasserstein Gradient Flows


Dec 01, 2020
Abdul Fatir Ansari, Ming Liang Ang, Harold Soh

Add code

* Preprint 

   Access Paper or Ask Questions

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

Efficient Exploration of Reward Functions in Inverse Reinforcement Learning via Bayesian Optimization


Nov 17, 2020
Sreejith Balakrishnan, Quoc Phong Nguyen, Bryan Kian Hsiang Low, Harold Soh

Add code

* Accepted to 34th Conference on Neural Information Processing Systems (NeurIPS 2020). Includes Appendix. 21 pages 

   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
>>