Alert button
Picture for Richard S. Sutton

Richard S. Sutton

Alert button

A Note on Stability in Asynchronous Stochastic Approximation without Communication Delays

Dec 22, 2023
Huizhen Yu, Yi Wan, Richard S. Sutton

Viaarxiv icon

Iterative Option Discovery for Planning, by Planning

Oct 02, 2023
Kenny Young, Richard S. Sutton

Figure 1 for Iterative Option Discovery for Planning, by Planning
Figure 2 for Iterative Option Discovery for Planning, by Planning
Figure 3 for Iterative Option Discovery for Planning, by Planning
Figure 4 for Iterative Option Discovery for Planning, by Planning
Viaarxiv icon

Value-aware Importance Weighting for Off-policy Reinforcement Learning

Jun 27, 2023
Kristopher De Asis, Eric Graves, Richard S. Sutton

Figure 1 for Value-aware Importance Weighting for Off-policy Reinforcement Learning
Figure 2 for Value-aware Importance Weighting for Off-policy Reinforcement Learning
Figure 3 for Value-aware Importance Weighting for Off-policy Reinforcement Learning
Figure 4 for Value-aware Importance Weighting for Off-policy Reinforcement Learning
Viaarxiv icon

Maintaining Plasticity in Deep Continual Learning

Jun 23, 2023
Shibhansh Dohare, J. Fernando Hernandez-Garcia, Parash Rahman, Richard S. Sutton, A. Rupam Mahmood

Figure 1 for Maintaining Plasticity in Deep Continual Learning
Figure 2 for Maintaining Plasticity in Deep Continual Learning
Figure 3 for Maintaining Plasticity in Deep Continual Learning
Figure 4 for Maintaining Plasticity in Deep Continual Learning
Viaarxiv icon

On Convergence of Average-Reward Off-Policy Control Algorithms in Weakly-Communicating MDPs

Sep 30, 2022
Yi Wan, Richard S. Sutton

Figure 1 for On Convergence of Average-Reward Off-Policy Control Algorithms in Weakly-Communicating MDPs
Figure 2 for On Convergence of Average-Reward Off-Policy Control Algorithms in Weakly-Communicating MDPs
Figure 3 for On Convergence of Average-Reward Off-Policy Control Algorithms in Weakly-Communicating MDPs
Figure 4 for On Convergence of Average-Reward Off-Policy Control Algorithms in Weakly-Communicating MDPs
Viaarxiv icon

The Alberta Plan for AI Research

Aug 23, 2022
Richard S. Sutton, Michael H. Bowling, Patrick M. Pilarski

Figure 1 for The Alberta Plan for AI Research
Figure 2 for The Alberta Plan for AI Research
Viaarxiv icon

Doubly-Asynchronous Value Iteration: Making Value Iteration Asynchronous in Actions

Jul 04, 2022
Tian Tian, Kenny Young, Richard S. Sutton

Figure 1 for Doubly-Asynchronous Value Iteration: Making Value Iteration Asynchronous in Actions
Figure 2 for Doubly-Asynchronous Value Iteration: Making Value Iteration Asynchronous in Actions
Figure 3 for Doubly-Asynchronous Value Iteration: Making Value Iteration Asynchronous in Actions
Figure 4 for Doubly-Asynchronous Value Iteration: Making Value Iteration Asynchronous in Actions
Viaarxiv icon

Toward Discovering Options that Achieve Faster Planning

May 25, 2022
Yi Wan, Richard S. Sutton

Figure 1 for Toward Discovering Options that Achieve Faster Planning
Figure 2 for Toward Discovering Options that Achieve Faster Planning
Figure 3 for Toward Discovering Options that Achieve Faster Planning
Figure 4 for Toward Discovering Options that Achieve Faster Planning
Viaarxiv icon

The Quest for a Common Model of the Intelligent Decision Maker

Apr 08, 2022
Richard S. Sutton

Viaarxiv icon