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

Parallel Training of Deep Networks with Local Updates

Dec 07, 2020
Michael Laskin, Luke Metz, Seth Nabarrao, Mark Saroufim, Badreddine Noune, Carlo Luschi, Jascha Sohl-Dickstein, Pieter Abbeel

Figure 1 for Parallel Training of Deep Networks with Local Updates

Figure 2 for Parallel Training of Deep Networks with Local Updates

Figure 3 for Parallel Training of Deep Networks with Local Updates

Figure 4 for Parallel Training of Deep Networks with Local Updates

* First two authors - Michael Laskin and Luke Metz - contributed equally. Order was determined by a coin flip

Access Paper or Ask Questions

Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning

Oct 26, 2020
Younggyo Seo, Kimin Lee, Ignasi Clavera, Thanard Kurutach, Jinwoo Shin, Pieter Abbeel

Figure 1 for Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning

Figure 2 for Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning

Figure 3 for Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning

Figure 4 for Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning

* Accepted in NeurIPS2020. First two authors contributed equally, website: https://sites.google.com/view/trajectory-mcl code: https://github.com/younggyoseo/trajectory_mcl

Access Paper or Ask Questions

LaND: Learning to Navigate from Disengagements

Oct 09, 2020
Gregory Kahn, Pieter Abbeel, Sergey Levine

Figure 1 for LaND: Learning to Navigate from Disengagements

Figure 2 for LaND: Learning to Navigate from Disengagements

Figure 3 for LaND: Learning to Navigate from Disengagements

Figure 4 for LaND: Learning to Navigate from Disengagements

Access Paper or Ask Questions

Decoupling Representation Learning from Reinforcement Learning

Sep 30, 2020
Adam Stooke, Kimin Lee, Pieter Abbeel, Michael Laskin

Figure 1 for Decoupling Representation Learning from Reinforcement Learning

Figure 2 for Decoupling Representation Learning from Reinforcement Learning

Figure 3 for Decoupling Representation Learning from Reinforcement Learning

Figure 4 for Decoupling Representation Learning from Reinforcement Learning

* Improved related works and fixed code hyperlink

Access Paper or Ask Questions

Hybrid Discriminative-Generative Training via Contrastive Learning

Aug 10, 2020
Hao Liu, Pieter Abbeel

Figure 1 for Hybrid Discriminative-Generative Training via Contrastive Learning

Figure 2 for Hybrid Discriminative-Generative Training via Contrastive Learning

Figure 3 for Hybrid Discriminative-Generative Training via Contrastive Learning

Figure 4 for Hybrid Discriminative-Generative Training via Contrastive Learning

* Code: https://github.com/lhao499/HDGE

Access Paper or Ask Questions

Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learning

Aug 03, 2020
Xingyu Lu, Kimin Lee, Pieter Abbeel, Stas Tiomkin

Figure 1 for Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learning

Figure 2 for Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learning

Figure 3 for Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learning

Figure 4 for Dynamics Generalization via Information Bottleneck in Deep Reinforcement Learning

* 16 pages

Access Paper or Ask Questions