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

One-Shot Learning of Manipulation Skills with Online Dynamics Adaptation and Neural Network Priors

Aug 11, 2016
Justin Fu, Sergey Levine, Pieter Abbeel

Figure 1 for One-Shot Learning of Manipulation Skills with Online Dynamics Adaptation and Neural Network Priors

Figure 2 for One-Shot Learning of Manipulation Skills with Online Dynamics Adaptation and Neural Network Priors

Figure 3 for One-Shot Learning of Manipulation Skills with Online Dynamics Adaptation and Neural Network Priors

Figure 4 for One-Shot Learning of Manipulation Skills with Online Dynamics Adaptation and Neural Network Priors

Access Paper or Ask Questions

Benchmarking Deep Reinforcement Learning for Continuous Control

May 27, 2016
Yan Duan, Xi Chen, Rein Houthooft, John Schulman, Pieter Abbeel

Figure 1 for Benchmarking Deep Reinforcement Learning for Continuous Control

Figure 2 for Benchmarking Deep Reinforcement Learning for Continuous Control

Figure 3 for Benchmarking Deep Reinforcement Learning for Continuous Control

Figure 4 for Benchmarking Deep Reinforcement Learning for Continuous Control

* 14 pages, ICML 2016

Access Paper or Ask Questions

Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization

May 27, 2016
Chelsea Finn, Sergey Levine, Pieter Abbeel

Figure 1 for Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization

Figure 2 for Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization

Figure 3 for Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization

Figure 4 for Guided Cost Learning: Deep Inverse Optimal Control via Policy Optimization

* International Conference on Machine Learning (ICML), 2016, to appear

Access Paper or Ask Questions

End-to-End Training of Deep Visuomotor Policies

Apr 19, 2016
Sergey Levine, Chelsea Finn, Trevor Darrell, Pieter Abbeel

Figure 1 for End-to-End Training of Deep Visuomotor Policies

Figure 2 for End-to-End Training of Deep Visuomotor Policies

Figure 3 for End-to-End Training of Deep Visuomotor Policies

Figure 4 for End-to-End Training of Deep Visuomotor Policies

* updating with revisions for JMLR final version

Access Paper or Ask Questions

Deep Spatial Autoencoders for Visuomotor Learning

Mar 01, 2016
Chelsea Finn, Xin Yu Tan, Yan Duan, Trevor Darrell, Sergey Levine, Pieter Abbeel

Figure 1 for Deep Spatial Autoencoders for Visuomotor Learning

Figure 2 for Deep Spatial Autoencoders for Visuomotor Learning

Figure 3 for Deep Spatial Autoencoders for Visuomotor Learning

Figure 4 for Deep Spatial Autoencoders for Visuomotor Learning

* Published in the International Conference on Robotics and Automation (ICRA)

Access Paper or Ask Questions

Learning Deep Control Policies for Autonomous Aerial Vehicles with MPC-Guided Policy Search

Feb 16, 2016
Tianhao Zhang, Gregory Kahn, Sergey Levine, Pieter Abbeel

Figure 1 for Learning Deep Control Policies for Autonomous Aerial Vehicles with MPC-Guided Policy Search

Figure 2 for Learning Deep Control Policies for Autonomous Aerial Vehicles with MPC-Guided Policy Search

Figure 3 for Learning Deep Control Policies for Autonomous Aerial Vehicles with MPC-Guided Policy Search

Access Paper or Ask Questions

Gradient Estimation Using Stochastic Computation Graphs

Jan 05, 2016
John Schulman, Nicolas Heess, Theophane Weber, Pieter Abbeel

Figure 1 for Gradient Estimation Using Stochastic Computation Graphs

* Advances in Neural Information Processing Systems 28 (NIPS 2015)

Access Paper or Ask Questions

Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models

Nov 19, 2015
Bradly C. Stadie, Sergey Levine, Pieter Abbeel

Figure 1 for Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models

Figure 2 for Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models

Figure 3 for Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models

Figure 4 for Incentivizing Exploration In Reinforcement Learning With Deep Predictive Models

Access Paper or Ask Questions