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

Add to Chrome

Add to Firefox

Picture for Pieter Abbeel

Pieter Abbeel

Learning to Adapt: Meta-Learning for Model-Based Control

May 30, 2018
Ignasi Clavera, Anusha Nagabandi, Ronald S. Fearing, Pieter Abbeel, Sergey Levine, Chelsea Finn

Figure 1 for Learning to Adapt: Meta-Learning for Model-Based Control

Figure 2 for Learning to Adapt: Meta-Learning for Model-Based Control

Figure 3 for Learning to Adapt: Meta-Learning for Model-Based Control

Figure 4 for Learning to Adapt: Meta-Learning for Model-Based Control

* First 2 authors contributed equally. Website: https://sites.google.com/berkeley.edu/metaadaptivecontrol

Access Paper or Ask Questions

Universal Planning Networks

Apr 04, 2018
Aravind Srinivas, Allan Jabri, Pieter Abbeel, Sergey Levine, Chelsea Finn

Figure 1 for Universal Planning Networks

Figure 2 for Universal Planning Networks

Figure 3 for Universal Planning Networks

Figure 4 for Universal Planning Networks

* Videos available at https://sites.google.com/view/upn-public/home

Access Paper or Ask Questions

Domain Randomization and Generative Models for Robotic Grasping

Apr 03, 2018
Joshua Tobin, Lukas Biewald, Rocky Duan, Marcin Andrychowicz, Ankur Handa, Vikash Kumar, Bob McGrew, Jonas Schneider, Peter Welinder, Wojciech Zaremba, Pieter Abbeel

Figure 1 for Domain Randomization and Generative Models for Robotic Grasping

Figure 2 for Domain Randomization and Generative Models for Robotic Grasping

Figure 3 for Domain Randomization and Generative Models for Robotic Grasping

Figure 4 for Domain Randomization and Generative Models for Robotic Grasping

* 8 pages, 11 figures. Submitted to 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2018)

Access Paper or Ask Questions

Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines

Mar 20, 2018
Cathy Wu, Aravind Rajeswaran, Yan Duan, Vikash Kumar, Alexandre M Bayen, Sham Kakade, Igor Mordatch, Pieter Abbeel

Figure 1 for Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines

Figure 2 for Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines

Figure 3 for Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines

Figure 4 for Variance Reduction for Policy Gradient with Action-Dependent Factorized Baselines

* Accepted to ICLR 2018, Oral (2%)

Access Paper or Ask Questions

Accelerated Methods for Deep Reinforcement Learning

Mar 07, 2018
Adam Stooke, Pieter Abbeel

Figure 1 for Accelerated Methods for Deep Reinforcement Learning

Figure 2 for Accelerated Methods for Deep Reinforcement Learning

Figure 3 for Accelerated Methods for Deep Reinforcement Learning

Figure 4 for Accelerated Methods for Deep Reinforcement Learning

Access Paper or Ask Questions