
Albert Zhan*, Philip Zhao*, Lerrel Pinto, Pieter Abbeel, Michael Laskin
In Submission, 2020
A Framework for Efficient Robotic Manipulation (FERM) enables real robots to solve sparsereward tasks from pixels in minutes.


Michael Laskin*, Luke Metz*, Seth Nabarrao, Mark Saroufim, Badreddine Noune, Carlo Luschi, Jascha SohlDickstein, Pieter Abbeel
In Submission, 2020
paper
/ twitter
Local learning, an alternative to global backpropagation, improves the efficiency of training deep nets in the highcompute regime.


Adam Stooke, Kimin Lee, Pieter Abbeel, Michael Laskin
In Submission, 2020
paper
/ code
/ twitter
First algorithm that decouples unsupervised learning from reinforcement learning while matching or outperforming stateoftheart endtoend RL.


Kimin Lee, Michael Laskin, Aravind Srinivas, Pieter Abbeel
In Submission, 2020
paper
/ code
Developed a unified framework for utilizing ensembles to greatly stabilize training of both statebased and pixelbased RL algorithms.


Michael Laskin*, Kimin Lee*, Adam Stooke, Lerrel Pinto, Pieter Abbeel, Aravind Srinivas
NeurIPS Spotlight (top 3% of submissions), 2020
paper
/ code
/ twitter
/ press
First extensive study of image augmentation in the RL setting. Showed that simple RL algorithms with augmented data achieve SOTA results on many common RL benchmarks.


Michael Laskin*, Aravind Srinivas*, Pieter Abbeel
ICML, 2020
paper
/ code
/ twitter
Showed for the first time that RL from pixels can be as efficient as RL from state by leveraging unsupervised contrastive representations.


Scott Emmons*, Ajay Jain*, Michael Laskin*, Thanard Kurutach, Pieter Abbeel, Deepak Pathak
NeurIPS, 2020
paper
/ video
/ code
Introduced novel state aggregation criterium  twoway consistency (TWC)  and utilized it to make any semiparametric graphical method more robust. Proved theoretically that TWC enables nearoptimal search.


Michael Laskin, Thanard Kurutach, Pieter Abbeel
NeurIPS Deep Reinforcement Learning Workshop, 2019
paper
Discrete representations help reduce the size of the encoded observation space. We showed how utilizing a discrete bottleneck can improve goalconditioned RL from pixels.

Physics Research
During my physics PhD I studied manybody quantum
systems such as the Fractional Quantum Hall Effect, and discovered
a universal topological characteristic of such states.
Note: in theoretical physics alphabetical order is the usual convention for authorship.

Emergent conformal symmetry and geometric transport properties of quantum Hall states on singular surfaces
T. Can, Y.H. Chiu, M. Laskin, P. Wiegmann
Physical review letters 117 (26), 266803, 2016

Population of the giant pairing vibration
M. Laskin, R.F. Casten, A.O. Macchiavelli, R.M. Clark, D. Bucurescu
Physical Review C 93 (3), 034321, 2016

Collective field theory for quantum Hall states
T. Can, M. Laskin, P. Wiegmann
Physical Review B 92 (23), 235141 , 2015

Geometry of quantum Hall states: Gravitational anomaly and transport coefficients
T. Can, M. Laskin, P. Wiegmann
Annals of Physics 362, 752794, 2015

Fractional quantum Hall effect in a curved space: gravitational anomaly and electromagnetic response
T. Can, M. Laskin, P. Wiegmann
Physical review letters 113 (4), 046803, 2014

Field Theory for Fractional Quantum Hall States
T. Can, M. Laskin, P. Wiegmann
arXiv preprint arXiv:1412.8716, 2014

Some Aspects of the GiantPairing Vibration
A.O. Macchiavelli, R.M. Clark, M. Laskin, R.F. Casten
Bulletin of the American Physical Society, 2012

