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

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Linguistic communication as (inverse) reward design


Apr 11, 2022
Theodore R. Sumers, Robert D. Hawkins, Mark K. Ho, Thomas L. Griffiths, Dylan Hadfield-Menell

* 6 pages, 3 figures. Accepted at Learning from Natural Language Supervision workshop (ACL 2022) 

   Access Paper or Ask Questions

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

On the Expressivity of Markov Reward


Nov 01, 2021
David Abel, Will Dabney, Anna Harutyunyan, Mark K. Ho, Michael L. Littman, Doina Precup, Satinder Singh

* Accepted to 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

Cognitive science as a source of forward and inverse models of human decisions for robotics and control


Sep 01, 2021
Mark K. Ho, Thomas L. Griffiths

* Invited submission for Annual Review of Control, Robotics, and Autonomous Systems 

   Access Paper or Ask Questions

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

Extending rational models of communication from beliefs to actions


May 25, 2021
Theodore R. Sumers, Robert D. Hawkins, Mark K. Ho, Thomas L. Griffiths

* 7 pages, 4 figures. Proceedings for the 43rd Annual Meeting of the Cognitive Science Society 

   Access Paper or Ask Questions

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

Control of mental representations in human planning


May 14, 2021
Mark K. Ho, David Abel, Carlos G. Correa, Michael L. Littman, Jonathan D. Cohen, Thomas L. Griffiths


   Access Paper or Ask Questions

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

Show or Tell? Demonstration is More Robust to Changes in Shared Perception than Explanation


Dec 16, 2020
Theodore R. Sumers, Mark K. Ho, Thomas L. Griffiths

* 7 pages, 4 figures. Proceedings for the 42nd Annual Meeting of the Cognitive Science Society 

   Access Paper or Ask Questions

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

Learning Rewards from Linguistic Feedback


Sep 30, 2020
Theodore R. Sumers, Mark K. Ho, Robert D. Hawkins, Karthik Narasimhan, Thomas L. Griffiths

* 9 pages, 4 figures 

   Access Paper or Ask Questions

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

Using Machine Teaching to Investigate Human Assumptions when Teaching Reinforcement Learners


Sep 05, 2020
Yun-Shiuan Chuang, Xuezhou Zhang, Yuzhe Ma, Mark K. Ho, Joseph L. Austerweil, Xiaojin Zhu

* 21 pages, 4 figures 

   Access Paper or Ask Questions

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

Resource-rational Task Decomposition to Minimize Planning Costs


Jul 27, 2020
Carlos G. Correa, Mark K. Ho, Fred Callaway, Thomas L. Griffiths

* The first two authors contributed equally. To appear in Proceedings of the 42nd Annual Conference of the Cognitive Science Society (CogSci 2020) 

   Access Paper or Ask Questions

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

The Efficiency of Human Cognition Reflects Planned Information Processing


Feb 13, 2020
Mark K. Ho, David Abel, Jonathan D. Cohen, Michael L. Littman, Thomas L. Griffiths

* 13 pg (incl. supplemental materials); included in Proceedings of the 34th AAAI Conference on Artificial Intelligence 

   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
>>