Michael (Misha) Laskin

verfied profile

Postdoc at Berkeley AI Research in UC Berkeley working with Pieter Abbeel. Mostly focusing on unsupervised learning and deep reinforcement learning.

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
Parallel Training of Deep Networks with Local Updates

Deep learning models trained on large data sets have been widely success...
12/07/2020 ∙ by Michael (Misha) Laskin, et al. ∙ 8 ∙ share

read it
Decoupling Representation Learning from Reinforcement Learning

In an effort to overcome limitations of reward-driven feature learning i...
09/14/2020 ∙ by Adam Stooke, et al. ∙ 22 ∙ share

read it
SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning

Model-free deep reinforcement learning (RL) has been successful in a ran...
07/09/2020 ∙ by Kimin Lee, et al. ∙ 66 ∙ 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
CURL: Contrastive Unsupervised Representations for Reinforcement Learning

We present CURL: Contrastive Unsupervised Representations for Reinforcem...
04/08/2020 ∙ by Aravind Srinivas, et al. ∙ 23 ∙ share

read it
Sparse Graphical Memory for Robust Planning

To operate effectively in the real world, artificial agents must act fro...
03/13/2020 ∙ by Michael (Misha) Laskin, et al. ∙ 17 ∙ share

read it
Roof Age Determination for the Automated Site-Selection of Rooftop Solar

Rooftop solar is one of the most promising tools for drawing down greenh...
01/08/2020 ∙ by Chris Heinrich, et al. ∙ 1 ∙ share

read it

Michael (Misha) Laskin

Featured Co-authors

Pieter Abbeel

Jascha Sohl-Dickstein

Lerrel Pinto

Deepak Pathak

Luke Metz

Kimin Lee

Ajay Jain

Thanard Kurutach

Adam Stooke

Aravind Srinivas

Carlo Luschi

A Framework for Efficient Robotic Manipulation

Parallel Training of Deep Networks with Local Updates

Decoupling Representation Learning from Reinforcement Learning

SUNRISE: A Simple Unified Framework for Ensemble Learning in Deep Reinforcement Learning

Reinforcement Learning with Augmented Data

CURL: Contrastive Unsupervised Representations for Reinforcement Learning

Sparse Graphical Memory for Robust Planning

Roof Age Determination for the Automated Site-Selection of Rooftop Solar