Marcin Andrychowicz
Marcin Andrychowicz
OpenAI
Verified email at openai.com
TitleCited byYear
Learning to learn by gradient descent by gradient descent
M Andrychowicz, M Denil, S Gomez, MW Hoffman, D Pfau, T Schaul, ...
Advances in neural information processing systems, 3981-3989, 2016
5232016
Hindsight experience replay
M Andrychowicz, F Wolski, A Ray, J Schneider, R Fong, P Welinder, ...
Advances in Neural Information Processing Systems, 5048-5058, 2017
3062017
Secure multiparty computations on bitcoin
M Andrychowicz, S Dziembowski, D Malinowski, L Mazurek
2014 IEEE Symposium on Security and Privacy, 443-458, 2014
2682014
One-shot imitation learning
Y Duan, M Andrychowicz, B Stadie, OAIJ Ho, J Schneider, I Sutskever, ...
Advances in neural information processing systems, 1087-1098, 2017
1982017
Parameter space noise for exploration
M Plappert, R Houthooft, P Dhariwal, S Sidor, RY Chen, X Chen, T Asfour, ...
arXiv preprint arXiv:1706.01905, 2017
1552017
Sim-to-real transfer of robotic control with dynamics randomization
XB Peng, M Andrychowicz, W Zaremba, P Abbeel
2018 IEEE International Conference on Robotics and Automation (ICRA), 1-8, 2018
1482018
Learning dexterous in-hand manipulation
M Andrychowicz, B Baker, M Chociej, R Jozefowicz, B McGrew, ...
arXiv preprint arXiv:1808.00177, 2018
1132018
Fair two-party computations via bitcoin deposits
M Andrychowicz, S Dziembowski, D Malinowski, Ł Mazurek
International Conference on Financial Cryptography and Data Security, 105-121, 2014
1062014
Neural random-access machines
K Kurach, M Andrychowicz, I Sutskever
arXiv preprint arXiv:1511.06392, 2015
982015
Overcoming exploration in reinforcement learning with demonstrations
A Nair, B McGrew, M Andrychowicz, W Zaremba, P Abbeel
2018 IEEE International Conference on Robotics and Automation (ICRA), 6292-6299, 2018
972018
Multi-goal reinforcement learning: Challenging robotics environments and request for research
M Plappert, M Andrychowicz, A Ray, B McGrew, B Baker, G Powell, ...
arXiv preprint arXiv:1802.09464, 2018
582018
Asymmetric actor critic for image-based robot learning
L Pinto, M Andrychowicz, P Welinder, W Zaremba, P Abbeel
arXiv preprint arXiv:1710.06542, 2017
552017
On the malleability of bitcoin transactions
M Andrychowicz, S Dziembowski, D Malinowski, Ł Mazurek
International Conference on Financial Cryptography and Data Security, 1-18, 2015
422015
Learning efficient algorithms with hierarchical attentive memory
M Andrychowicz, K Kurach
arXiv preprint arXiv:1602.03218, 2016
402016
Domain randomization and generative models for robotic grasping
J Tobin, L Biewald, R Duan, M Andrychowicz, A Handa, V Kumar, ...
2018 IEEE/RSJ International Conference on Intelligent Robots and Systems …, 2018
372018
Pow-based distributed cryptography with no trusted setup
M Andrychowicz, S Dziembowski
Annual Cryptology Conference, 379-399, 2015
332015
Modeling bitcoin contracts by timed automata
M Andrychowicz, S Dziembowski, D Malinowski, Ł Mazurek
International Conference on Formal Modeling and Analysis of Timed Systems, 7-22, 2014
232014
Distributed Cryptography Based on the Proofs of Work.
M Andrychowicz, S Dziembowski
IACR Cryptology ePrint Archive 2014, 796, 2014
222014
Circuit Compilers with Leakage Rate
M Andrychowicz, S Dziembowski, S Faust
Annual International Conference on the Theory and Applications of …, 2016
162016
How to deal with malleability of bitcoin transactions
M Andrychowicz, S Dziembowski, D Malinowski, Ł Mazurek
arXiv preprint arXiv:1312.3230, 2013
152013
The system can't perform the operation now. Try again later.
Articles 1–20