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

Add to Chrome

Add to Firefox

Picture for Nathan Lambert

Nathan Lambert

Investigating Compounding Prediction Errors in Learned Dynamics Models

Mar 17, 2022
Nathan Lambert, Kristofer Pister, Roberto Calandra

Figure 1 for Investigating Compounding Prediction Errors in Learned Dynamics Models

Figure 2 for Investigating Compounding Prediction Errors in Learned Dynamics Models

Figure 3 for Investigating Compounding Prediction Errors in Learned Dynamics Models

Figure 4 for Investigating Compounding Prediction Errors in Learned Dynamics Models

* 25 pages, 19 figures

Access Paper or Ask Questions

Choices, Risks, and Reward Reports: Charting Public Policy for Reinforcement Learning Systems

Feb 11, 2022
Thomas Krendl Gilbert, Sarah Dean, Tom Zick, Nathan Lambert

* Center for Long Term Cybersecurity Whitepaper Series Feb. 2022; see release https://cltc.berkeley.edu/2022/02/08/reward-reports/
* 60 pages

Access Paper or Ask Questions

Axes for Sociotechnical Inquiry in AI Research

Apr 26, 2021
Sarah Dean, Thomas Krendl Gilbert, Nathan Lambert, Tom Zick

Figure 1 for Axes for Sociotechnical Inquiry in AI Research

Figure 2 for Axes for Sociotechnical Inquiry in AI Research

* 9 pages, 1 figure

Access Paper or Ask Questions

On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning

Feb 26, 2021
Baohe Zhang, Raghu Rajan, Luis Pineda, Nathan Lambert, André Biedenkapp, Kurtland Chua, Frank Hutter, Roberto Calandra

Figure 1 for On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning

Figure 2 for On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning

Figure 3 for On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning

Figure 4 for On the Importance of Hyperparameter Optimization for Model-based Reinforcement Learning

* 19 pages, accepted by AISTATS 2021

Access Paper or Ask Questions

AI Development for the Public Interest: From Abstraction Traps to Sociotechnical Risks

Feb 04, 2021
McKane Andrus, Sarah Dean, Thomas Krendl Gilbert, Nathan Lambert, Tom Zick

Figure 1 for AI Development for the Public Interest: From Abstraction Traps to Sociotechnical Risks

* 8 Pages

Access Paper or Ask Questions

Nonholonomic Yaw Control of an Underactuated Flying Robot with Model-based Reinforcement Learning

Sep 02, 2020
Nathan Lambert, Craig Schindler, Daniel Drew, Kristofer Pister

Figure 1 for Nonholonomic Yaw Control of an Underactuated Flying Robot with Model-based Reinforcement Learning

Figure 2 for Nonholonomic Yaw Control of an Underactuated Flying Robot with Model-based Reinforcement Learning

Figure 3 for Nonholonomic Yaw Control of an Underactuated Flying Robot with Model-based Reinforcement Learning

Figure 4 for Nonholonomic Yaw Control of an Underactuated Flying Robot with Model-based Reinforcement Learning

* 7 pages, 1 page appendix

Access Paper or Ask Questions