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

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Richard S. Sutton

An Empirical Comparison of Off-policy Prediction Learning Algorithms on the Collision Task


Jun 11, 2021
Sina Ghiassian, Richard S. Sutton


  Access Paper or Ask Questions

Planning with Expectation Models for Control


Apr 17, 2021
Katya Kudashkina, Yi Wan, Abhishek Naik, Richard S. Sutton


  Access Paper or Ask Questions

Does Standard Backpropagation Forget Less Catastrophically Than Adam?


Feb 20, 2021
Dylan R. Ashley, Sina Ghiassian, Richard S. Sutton

* 8 pages in main text + 3 pages of references + 6 pages of appendices, 6 figures in main text + 14 figures in appendices, 1 table in main text + 3 tables in appendices; source code available at https://github.com/dylanashley/catastrophic-forgetting/tree/arxiv 

  Access Paper or Ask Questions

Average-Reward Off-Policy Policy Evaluation with Function Approximation


Jan 08, 2021
Shangtong Zhang, Yi Wan, Richard S. Sutton, Shimon Whiteson


  Access Paper or Ask Questions

Understanding the Pathologies of Approximate Policy Evaluation when Combined with Greedification in Reinforcement Learning


Oct 28, 2020
Kenny Young, Richard S. Sutton


  Access Paper or Ask Questions

Document-editing Assistants and Model-based Reinforcement Learning as a Path to Conversational AI


Aug 27, 2020
Katya Kudashkina, Patrick M. Pilarski, Richard S. Sutton

* Currently under review 

  Access Paper or Ask Questions

Inverse Policy Evaluation for Value-based Sequential Decision-making


Aug 26, 2020
Alan Chan, Kris de Asis, Richard S. Sutton

* Submitted to NeurIPS 2020 

  Access Paper or Ask Questions

Learning and Planning in Average-Reward Markov Decision Processes


Jun 29, 2020
Yi Wan, Abhishek Naik, Richard S. Sutton


  Access Paper or Ask Questions

Learning Sparse Representations Incrementally in Deep Reinforcement Learning


Dec 09, 2019
J. Fernando Hernandez-Garcia, Richard S. Sutton


  Access Paper or Ask Questions

Discounted Reinforcement Learning is Not an Optimization Problem


Nov 16, 2019
Abhishek Naik, Roshan Shariff, Niko Yasui, Richard S. Sutton

* Accepted for presentation at the Optimization Foundations of Reinforcement Learning Workshop at NeurIPS 2019 

  Access Paper or Ask Questions

Fixed-Horizon Temporal Difference Methods for Stable Reinforcement Learning


Sep 09, 2019
Kristopher De Asis, Alan Chan, Silviu Pitis, Richard S. Sutton, Daniel Graves


  Access Paper or Ask Questions

Planning with Expectation Models


Apr 03, 2019
Yi Wan, Muhammad Zaheer, Adam White, Martha White, Richard S. Sutton


  Access Paper or Ask Questions

Learning Feature Relevance Through Step Size Adaptation in Temporal-Difference Learning


Mar 08, 2019
Alex Kearney, Vivek Veeriah, Jaden Travnik, Patrick M. Pilarski, Richard S. Sutton


  Access Paper or Ask Questions

Should All Temporal Difference Learning Use Emphasis?


Mar 01, 2019
Xiang Gu, Sina Ghiassian, Richard S. Sutton


  Access Paper or Ask Questions

Understanding Multi-Step Deep Reinforcement Learning: A Systematic Study of the DQN Target


Feb 07, 2019
J. Fernando Hernandez-Garcia, Richard S. Sutton


  Access Paper or Ask Questions

Online Off-policy Prediction


Nov 06, 2018
Sina Ghiassian, Andrew Patterson, Martha White, Richard S. Sutton, Adam White

* 68 pages 

  Access Paper or Ask Questions

Predicting Periodicity with Temporal Difference Learning


Sep 20, 2018
Kristopher De Asis, Brendan Bennett, Richard S. Sutton


  Access Paper or Ask Questions

Two geometric input transformation methods for fast online reinforcement learning with neural nets


Sep 06, 2018
Sina Ghiassian, Huizhen Yu, Banafsheh Rafiee, Richard S. Sutton

* 16 pages 

  Access Paper or Ask Questions

Per-decision Multi-step Temporal Difference Learning with Control Variates


Jul 05, 2018
Kristopher De Asis, Richard S. Sutton

* (2018). In Conference on Uncertainty in Artificial Intelligence. http://auai.org/uai2018/proceedings/papers/282.pdf 

  Access Paper or Ask Questions

Multi-step Reinforcement Learning: A Unifying Algorithm


Jun 11, 2018
Kristopher De Asis, J. Fernando Hernandez-Garcia, G. Zacharias Holland, Richard S. Sutton

* (2018). In AAAI Conference on Artificial Intelligence. https://www.aaai.org/ocs/index.php/AAAI/AAAI18/paper/view/16294 
* Appeared at the Thirty-Second AAAI Conference on Artificial Intelligence (AAAI-18) 

  Access Paper or Ask Questions

Integrating Episodic Memory into a Reinforcement Learning Agent using Reservoir Sampling


Jun 01, 2018
Kenny J. Young, Richard S. Sutton, Shuo Yang


  Access Paper or Ask Questions

A Deeper Look at Experience Replay


Apr 30, 2018
Shangtong Zhang, Richard S. Sutton

* NIPS 2017 Deep Reinforcement Learning Symposium 

  Access Paper or Ask Questions

TIDBD: Adapting Temporal-difference Step-sizes Through Stochastic Meta-descent


Apr 10, 2018
Alex Kearney, Vivek Veeriah, Jaden B. Travnik, Richard S. Sutton, Patrick M. Pilarski

* Version as submitted to the 31st Conference on Neural Information Processing Systems (NIPS 2017) on May 19, 2017. 9 pages, 5 figures. Extended version in preparation for journal submission 

  Access Paper or Ask Questions

Reactive Reinforcement Learning in Asynchronous Environments


Feb 16, 2018
Jaden B. Travnik, Kory W. Mathewson, Richard S. Sutton, Patrick M. Pilarski

* 11 pages, 7 figures, currently under journal peer review 

  Access Paper or Ask Questions

Directly Estimating the Variance of the 位-Return Using Temporal-Difference Methods


Feb 14, 2018
Craig Sherstan, Brendan Bennett, Kenny Young, Dylan R. Ashley, Adam White, Martha White, Richard S. Sutton


  Access Paper or Ask Questions

Communicative Capital for Prosthetic Agents


Nov 10, 2017
Patrick M. Pilarski, Richard S. Sutton, Kory W. Mathewson, Craig Sherstan, Adam S. R. Parker, Ann L. Edwards

* 33 pages, 10 figures; unpublished technical report undergoing peer review 

  Access Paper or Ask Questions