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

Generalized Hindsight for Reinforcement Learning

Feb 26, 2020
Alexander C. Li, Lerrel Pinto, Pieter Abbeel

Figure 1 for Generalized Hindsight for Reinforcement Learning

Figure 2 for Generalized Hindsight for Reinforcement Learning

Figure 3 for Generalized Hindsight for Reinforcement Learning

Figure 4 for Generalized Hindsight for Reinforcement Learning

Access Paper or Ask Questions

GACEM: Generalized Autoregressive Cross Entropy Method for Multi-Modal Black Box Constraint Satisfaction

Feb 17, 2020
Kourosh Hakhamaneshi, Keertana Settaluri, Pieter Abbeel, Vladimir Stojanovic

Figure 1 for GACEM: Generalized Autoregressive Cross Entropy Method for Multi-Modal Black Box Constraint Satisfaction

Figure 2 for GACEM: Generalized Autoregressive Cross Entropy Method for Multi-Modal Black Box Constraint Satisfaction

Figure 3 for GACEM: Generalized Autoregressive Cross Entropy Method for Multi-Modal Black Box Constraint Satisfaction

Figure 4 for GACEM: Generalized Autoregressive Cross Entropy Method for Multi-Modal Black Box Constraint Satisfaction

Access Paper or Ask Questions

BADGR: An Autonomous Self-Supervised Learning-Based Navigation System

Feb 13, 2020
Gregory Kahn, Pieter Abbeel, Sergey Levine

Figure 1 for BADGR: An Autonomous Self-Supervised Learning-Based Navigation System

Figure 2 for BADGR: An Autonomous Self-Supervised Learning-Based Navigation System

Figure 3 for BADGR: An Autonomous Self-Supervised Learning-Based Navigation System

Figure 4 for BADGR: An Autonomous Self-Supervised Learning-Based Navigation System

Access Paper or Ask Questions

Preventing Imitation Learning with Adversarial Policy Ensembles

Jan 31, 2020
Albert Zhan, Stas Tiomkin, Pieter Abbeel

Figure 1 for Preventing Imitation Learning with Adversarial Policy Ensembles

Figure 2 for Preventing Imitation Learning with Adversarial Policy Ensembles

Figure 3 for Preventing Imitation Learning with Adversarial Policy Ensembles

Figure 4 for Preventing Imitation Learning with Adversarial Policy Ensembles

Access Paper or Ask Questions

Predictive Coding for Boosting Deep Reinforcement Learning with Sparse Rewards

Dec 21, 2019
Xingyu Lu, Stas Tiomkin, Pieter Abbeel

Figure 1 for Predictive Coding for Boosting Deep Reinforcement Learning with Sparse Rewards

Figure 2 for Predictive Coding for Boosting Deep Reinforcement Learning with Sparse Rewards

Figure 3 for Predictive Coding for Boosting Deep Reinforcement Learning with Sparse Rewards

Figure 4 for Predictive Coding for Boosting Deep Reinforcement Learning with Sparse Rewards

Access Paper or Ask Questions

AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos

Dec 10, 2019
Laura Smith, Nikita Dhawan, Marvin Zhang, Pieter Abbeel, Sergey Levine

Figure 1 for AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos

Figure 2 for AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos

Figure 3 for AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos

Figure 4 for AVID: Learning Multi-Stage Tasks via Pixel-Level Translation of Human Videos

* Under review at the International Conference on Robotics and Automation (ICRA), 2020

Access Paper or Ask Questions

Learning Efficient Representation for Intrinsic Motivation

Dec 09, 2019
Ruihan Zhao, Stas Tiomkin, Pieter Abbeel

Figure 1 for Learning Efficient Representation for Intrinsic Motivation

Figure 2 for Learning Efficient Representation for Intrinsic Motivation

Figure 3 for Learning Efficient Representation for Intrinsic Motivation

Figure 4 for Learning Efficient Representation for Intrinsic Motivation

Access Paper or Ask Questions

Adaptive Online Planning for Continual Lifelong Learning

Dec 03, 2019
Kevin Lu, Igor Mordatch, Pieter Abbeel

Figure 1 for Adaptive Online Planning for Continual Lifelong Learning

Figure 2 for Adaptive Online Planning for Continual Lifelong Learning

Figure 3 for Adaptive Online Planning for Continual Lifelong Learning

Figure 4 for Adaptive Online Planning for Continual Lifelong Learning

* NeurIPS Deep RL 2019

Access Paper or Ask Questions