Alert button
Picture for Martha White

Martha White

Alert button

Maxmin Q-learning: Controlling the Estimation Bias of Q-learning

Feb 16, 2020
Qingfeng Lan, Yangchen Pan, Alona Fyshe, Martha White

Figure 1 for Maxmin Q-learning: Controlling the Estimation Bias of Q-learning
Figure 2 for Maxmin Q-learning: Controlling the Estimation Bias of Q-learning
Figure 3 for Maxmin Q-learning: Controlling the Estimation Bias of Q-learning
Figure 4 for Maxmin Q-learning: Controlling the Estimation Bias of Q-learning
Viaarxiv icon

An implicit function learning approach for parametric modal regression

Feb 14, 2020
Yangchen Pan, Ehsan Imani, Martha White, Amir-massoud Farahmand

Figure 1 for An implicit function learning approach for parametric modal regression
Figure 2 for An implicit function learning approach for parametric modal regression
Figure 3 for An implicit function learning approach for parametric modal regression
Figure 4 for An implicit function learning approach for parametric modal regression
Viaarxiv icon

Is Fast Adaptation All You Need?

Oct 03, 2019
Khurram Javed, Hengshuai Yao, Martha White

Figure 1 for Is Fast Adaptation All You Need?
Figure 2 for Is Fast Adaptation All You Need?
Figure 3 for Is Fast Adaptation All You Need?
Viaarxiv icon

Meta-descent for Online, Continual Prediction

Jul 17, 2019
Andrew Jacobsen, Matthew Schlegel, Cameron Linke, Thomas Degris, Adam White, Martha White

Figure 1 for Meta-descent for Online, Continual Prediction
Figure 2 for Meta-descent for Online, Continual Prediction
Figure 3 for Meta-descent for Online, Continual Prediction
Figure 4 for Meta-descent for Online, Continual Prediction
Viaarxiv icon

Hill Climbing on Value Estimates for Search-control in Dyna

Jul 04, 2019
Yangchen Pan, Hengshuai Yao, Amir-massoud Farahmand, Martha White

Figure 1 for Hill Climbing on Value Estimates for Search-control in Dyna
Figure 2 for Hill Climbing on Value Estimates for Search-control in Dyna
Figure 3 for Hill Climbing on Value Estimates for Search-control in Dyna
Figure 4 for Hill Climbing on Value Estimates for Search-control in Dyna
Viaarxiv icon

Adapting Behaviour via Intrinsic Reward: A Survey and Empirical Study

Jun 19, 2019
Cam Linke, Nadia M. Ady, Martha White, Thomas Degris, Adam White

Figure 1 for Adapting Behaviour via Intrinsic Reward: A Survey and Empirical Study
Figure 2 for Adapting Behaviour via Intrinsic Reward: A Survey and Empirical Study
Figure 3 for Adapting Behaviour via Intrinsic Reward: A Survey and Empirical Study
Figure 4 for Adapting Behaviour via Intrinsic Reward: A Survey and Empirical Study
Viaarxiv icon

Importance Resampling for Off-policy Prediction

Jun 11, 2019
Matthew Schlegel, Wesley Chung, Daniel Graves, Jian Qian, Martha White

Figure 1 for Importance Resampling for Off-policy Prediction
Figure 2 for Importance Resampling for Off-policy Prediction
Figure 3 for Importance Resampling for Off-policy Prediction
Figure 4 for Importance Resampling for Off-policy Prediction
Viaarxiv icon

Meta-Learning Representations for Continual Learning

May 29, 2019
Khurram Javed, Martha White

Figure 1 for Meta-Learning Representations for Continual Learning
Figure 2 for Meta-Learning Representations for Continual Learning
Figure 3 for Meta-Learning Representations for Continual Learning
Figure 4 for Meta-Learning Representations for Continual Learning
Viaarxiv icon