b'Lerrel Pinto'

GEM: Group Enhanced Model for Learning Dynamical Control Systems

Learning the dynamics of a physical system wherein an autonomous agent o...
04/07/2021 ∙ by Philippe Hansen-Estruch, et al. ∙ 0 ∙ share

read it
Simultaneous Navigation and Construction Benchmarking Environments

We need intelligent robots for mobile construction, the process of navig...
03/31/2021 ∙ by Wenyu Han, et al. ∙ 6 ∙ share

read it
Task-Agnostic Morphology Evolution

Deep reinforcement learning primarily focuses on learning behavior, usua...
02/25/2021 ∙ by Donald J. Hejna III, et al. ∙ 0 ∙ share

read it
Reinforcement Learning with Prototypical Representations

Learning effective representations in image-based environments is crucia...
02/22/2021 ∙ by Denis Yarats, et al. ∙ 21 ∙ share

read it
A Framework for Efficient Robotic Manipulation

Data-efficient learning of manipulation policies from visual observation...
12/14/2020 ∙ by Albert Zhan, et al. ∙ 8 ∙ share

read it
Robust Policies via Mid-Level Visual Representations: An Experimental Study in Manipulation and Navigation

Vision-based robotics often separates the control loop into one module f...
11/13/2020 ∙ by Bryan Chen, et al. ∙ 0 ∙ share

read it
Self-Supervised Policy Adaptation during Deployment

In most real world scenarios, a policy trained by reinforcement learning...
07/08/2020 ∙ by Nicklas Hansen, et al. ∙ 4 ∙ share

read it
Automatic Curriculum Learning through Value Disagreement

Continually solving new, unsolved tasks is the key to learning diverse b...
06/17/2020 ∙ by Yunzhi Zhang, et al. ∙ 10 ∙ share

read it
Reinforcement Learning with Augmented Data

Learning from visual observations is a fundamental yet challenging probl...
04/30/2020 ∙ by Michael (Misha) Laskin, et al. ∙ 14 ∙ share

read it
State-Only Imitation Learning for Dexterous Manipulation

Dexterous manipulation has been a long-standing challenge in robotics. R...
04/07/2020 ∙ by Ilija Radosavovic, et al. ∙ 1 ∙ share

read it
Learning Predictive Representations for Deformable Objects Using Contrastive Estimation

Using visual model-based learning for deformable object manipulation is ...
03/11/2020 ∙ by Wilson Yan, et al. ∙ 13 ∙ share

read it
Hierarchically Decoupled Imitation for Morphological Transfer

Learning long-range behaviors on complex high-dimensional agents is a fu...
03/03/2020 ∙ by Donald J. Hejna III, et al. ∙ 10 ∙ share

read it
Generalized Hindsight for Reinforcement Learning

One of the key reasons for the high sample complexity in reinforcement l...
02/26/2020 ∙ by Alexander C. Li, et al. ∙ 26 ∙ share

read it
Learning to Manipulate Deformable Objects without Demonstrations

In this paper we tackle the problem of deformable object manipulation th...
10/29/2019 ∙ by Yilin Wu, et al. ∙ 10 ∙ share

read it
Environment Probing Interaction Policies

A key challenge in reinforcement learning (RL) is environment generaliza...
07/26/2019 ∙ by Wenxuan Zhou, et al. ∙ 0 ∙ share

read it
PyRobot: An Open-source Robotics Framework for Research and Benchmarking

This paper introduces PyRobot, an open-source robotics framework for res...
06/19/2019 ∙ by Adithyavairavan Murali, et al. ∙ 9 ∙ share

read it
Robot Learning via Human Adversarial Games

Much work in robotics has focused on "human-in-the-loop" learning techni...
03/02/2019 ∙ by Jiali Duan, et al. ∙ 0 ∙ share

read it
Sample-Efficient Learning of Nonprehensile Manipulation Policies via Physics-Based Informed State Distributions

This paper proposes a sample-efficient yet simple approach to learning c...
10/24/2018 ∙ by Lerrel Pinto, et al. ∙ 2 ∙ share

read it
Multiple Interactions Made Easy (MIME): Large Scale Demonstrations Data for Imitation

In recent years, we have seen an emergence of data-driven approaches in ...
10/16/2018 ∙ by Pratyusha Sharma, et al. ∙ 0 ∙ share

read it
Robot Learning in Homes: Improving Generalization and Reducing Dataset Bias

Data-driven approaches to solving robotic tasks have gained a lot of tra...
07/18/2018 ∙ by Abhinav Gupta, et al. ∙ 10 ∙ share

read it
Asymmetric Actor Critic for Image-Based Robot Learning

Deep reinforcement learning (RL) has proven a powerful technique in many...
10/18/2017 ∙ by Lerrel Pinto, et al. ∙ 0 ∙ share

read it
Predictive-State Decoders: Encoding the Future into Recurrent Networks

Recurrent neural networks (RNNs) are a vital modeling technique that rel...
09/25/2017 ∙ by Arun Venkatraman, et al. ∙ 0 ∙ share

read it
CASSL: Curriculum Accelerated Self-Supervised Learning

Recent self-supervised learning approaches focus on using a few thousand...
08/04/2017 ∙ by Adithyavairavan Murali, et al. ∙ 0 ∙ share

read it
Robust Adversarial Reinforcement Learning

Deep neural networks coupled with fast simulation and improved computati...
03/08/2017 ∙ by Lerrel Pinto, et al. ∙ 0 ∙ share

read it
Supervision via Competition: Robot Adversaries for Learning Tasks

There has been a recent paradigm shift in robotics to data-driven learni...
10/05/2016 ∙ by Lerrel Pinto, et al. ∙ 0 ∙ share

read it
Learning to Push by Grasping: Using multiple tasks for effective learning

Recently, end-to-end learning frameworks are gaining prevalence in the f...
09/28/2016 ∙ by Lerrel Pinto, et al. ∙ 0 ∙ share

read it
The Curious Robot: Learning Visual Representations via Physical Interactions

What is the right supervisory signal to train visual representations? Cu...
04/05/2016 ∙ by Lerrel Pinto, et al. ∙ 0 ∙ share

read it

Lerrel Pinto

Featured Co-authors

Pieter Abbeel

Silvio Savarese

Jitendra Malik

C. -C. Jay Kuo

Qian Wang

Abhinav Gupta

Yu Sun

Byron Boots

Dong Liu

Alexei A. Efros

Alessandro Lazaric

GEM: Group Enhanced Model for Learning Dynamical Control Systems

Simultaneous Navigation and Construction Benchmarking Environments

Task-Agnostic Morphology Evolution

Reinforcement Learning with Prototypical Representations

A Framework for Efficient Robotic Manipulation

Robust Policies via Mid-Level Visual Representations: An Experimental Study in Manipulation and Navigation

Self-Supervised Policy Adaptation during Deployment

Automatic Curriculum Learning through Value Disagreement

Reinforcement Learning with Augmented Data

State-Only Imitation Learning for Dexterous Manipulation

Learning Predictive Representations for Deformable Objects Using Contrastive Estimation

Hierarchically Decoupled Imitation for Morphological Transfer

Generalized Hindsight for Reinforcement Learning

Learning to Manipulate Deformable Objects without Demonstrations

Environment Probing Interaction Policies

PyRobot: An Open-source Robotics Framework for Research and Benchmarking

Robot Learning via Human Adversarial Games

Sample-Efficient Learning of Nonprehensile Manipulation Policies via Physics-Based Informed State Distributions

Multiple Interactions Made Easy (MIME): Large Scale Demonstrations Data for Imitation

Robot Learning in Homes: Improving Generalization and Reducing Dataset Bias

Asymmetric Actor Critic for Image-Based Robot Learning

Predictive-State Decoders: Encoding the Future into Recurrent Networks

CASSL: Curriculum Accelerated Self-Supervised Learning

Robust Adversarial Reinforcement Learning

Supervision via Competition: Robot Adversaries for Learning Tasks

Learning to Push by Grasping: Using multiple tasks for effective learning

The Curious Robot: Learning Visual Representations via Physical Interactions