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

Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation

Mar 06, 2018
Tianhao Zhang, Zoe McCarthy, Owen Jow, Dennis Lee, Xi Chen, Ken Goldberg, Pieter Abbeel

Figure 1 for Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation

Figure 2 for Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation

Figure 3 for Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation

Figure 4 for Deep Imitation Learning for Complex Manipulation Tasks from Virtual Reality Teleoperation

* First two authors contributed equally. Video available at https://sites.google.com/view/vrlfd/

Access Paper or Ask Questions

Sim-to-Real Transfer of Robotic Control with Dynamics Randomization

Mar 03, 2018
Xue Bin Peng, Marcin Andrychowicz, Wojciech Zaremba, Pieter Abbeel

Figure 1 for Sim-to-Real Transfer of Robotic Control with Dynamics Randomization

Figure 2 for Sim-to-Real Transfer of Robotic Control with Dynamics Randomization

Figure 3 for Sim-to-Real Transfer of Robotic Control with Dynamics Randomization

Figure 4 for Sim-to-Real Transfer of Robotic Control with Dynamics Randomization

Access Paper or Ask Questions

Overcoming Exploration in Reinforcement Learning with Demonstrations

Feb 25, 2018
Ashvin Nair, Bob McGrew, Marcin Andrychowicz, Wojciech Zaremba, Pieter Abbeel

Figure 1 for Overcoming Exploration in Reinforcement Learning with Demonstrations

Figure 2 for Overcoming Exploration in Reinforcement Learning with Demonstrations

Figure 3 for Overcoming Exploration in Reinforcement Learning with Demonstrations

Figure 4 for Overcoming Exploration in Reinforcement Learning with Demonstrations

* 8 pages, ICRA 2018

Access Paper or Ask Questions

A Simple Neural Attentive Meta-Learner

Feb 25, 2018
Nikhil Mishra, Mostafa Rohaninejad, Xi Chen, Pieter Abbeel

Figure 1 for A Simple Neural Attentive Meta-Learner

Figure 2 for A Simple Neural Attentive Meta-Learner

Figure 3 for A Simple Neural Attentive Meta-Learner

Figure 4 for A Simple Neural Attentive Meta-Learner

* iclr 2018 version

Access Paper or Ask Questions

Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments

Feb 23, 2018
Maruan Al-Shedivat, Trapit Bansal, Yuri Burda, Ilya Sutskever, Igor Mordatch, Pieter Abbeel

Figure 1 for Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments

Figure 2 for Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments

Figure 3 for Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments

Figure 4 for Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments

* Published as a conference paper at ICLR 2018

Access Paper or Ask Questions

Interpretable and Pedagogical Examples

Feb 14, 2018
Smitha Milli, Pieter Abbeel, Igor Mordatch

Figure 1 for Interpretable and Pedagogical Examples

Figure 2 for Interpretable and Pedagogical Examples

Figure 3 for Interpretable and Pedagogical Examples

Figure 4 for Interpretable and Pedagogical Examples

Access Paper or Ask Questions

One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning

Feb 05, 2018
Tianhe Yu, Chelsea Finn, Annie Xie, Sudeep Dasari, Tianhao Zhang, Pieter Abbeel, Sergey Levine

Figure 1 for One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning

Figure 2 for One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning

Figure 3 for One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning

Figure 4 for One-Shot Imitation from Observing Humans via Domain-Adaptive Meta-Learning

* First two authors contributed equally. Video available at https://sites.google.com/view/daml

Access Paper or Ask Questions