M
Marcin Andrychowicz
Researcher at Google
Publications - 51
Citations - 9149
Marcin Andrychowicz is an academic researcher from Google. The author has contributed to research in topics: Reinforcement learning & Cryptography. The author has an hindex of 28, co-authored 49 publications receiving 6638 citations. Previous affiliations of Marcin Andrychowicz include University of Warsaw & Nvidia.
Papers
More filters
Proceedings Article
Hindsight Experience Replay
Marcin Andrychowicz,Filip Wolski,Alex Ray,Jonas Schneider,Rachel Fong,Peter Welinder,Bob McGrew,Josh Tobin,OpenAI Pieter Abbeel,Wojciech Zaremba +9 more
TL;DR: A novel technique is presented which allows sample-efficient learning from rewards which are sparse and binary and therefore avoid the need for complicated reward engineering and may be seen as a form of implicit curriculum.
Proceedings ArticleDOI
Sim-to-Real Transfer of Robotic Control with Dynamics Randomization
TL;DR: In this article, the authors demonstrate a simple method to bridge the "reality gap" by randomizing the dynamics of the simulator during training and develop policies that are capable of adapting to very different dynamics, including ones that differ significantly from the dynamics on which the policies were trained.
Proceedings Article
Learning to learn by gradient descent by gradient descent
Marcin Andrychowicz,Misha Denil,Sergio Gomez,Matthew W. Hoffman,David Pfau,Tom Schaul,Brendan Shillingford,Nando de Freitas +7 more
TL;DR: This paper shows how the design of an optimization algorithm can be cast as a learning problem, allowing the algorithm to learn to exploit structure in the problems of interest in an automatic way.
Posted Content
Solving Rubik's Cube with a Robot Hand.
OpenAI,Ilge Akkaya,Marcin Andrychowicz,Maciek Chociej,Mateusz Litwin,Bob McGrew,Arthur Petron,Alex Paino,Matthias Plappert,Glenn Powell,Raphael Ribas,Jonas Schneider,Nikolas Tezak,Jerry Tworek,Peter Welinder,Lilian Weng,Qiming Yuan,Wojciech Zaremba,Lei M. Zhang +18 more
TL;DR: It is demonstrated that models trained only in simulation can be used to solve a manipulation problem of unprecedented complexity on a real robot, made possible by a novel algorithm, which is called automatic domain randomization (ADR), and a robot platform built for machine learning.
Proceedings ArticleDOI
Overcoming Exploration in Reinforcement Learning with Demonstrations
TL;DR: This work uses demonstrations to overcome the exploration problem and successfully learn to perform long-horizon, multi-step robotics tasks with continuous control such as stacking blocks with a robot arm.