🧑‍🔬 Marcin Andrychowicz

🏛️ Affiliations

🏢GoogleMountain View · United States2015–2023 · 10 paperscurrent🎓University of WarsawWarsaw · Poland2012–2016 · 15 papers🏢OpenAISan Francisco · United States2017–2018 · 3 papers

From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 1 more institution on single bylines are not listed.

🧭 Fields, topics and concepts

Of its works in our library, with the number of works on each.

📅 Works by year

2010s

📄 Papers

The most cited first (OpenAlex and our library).

1. Hindsight Experience Replay (2017 · 421 citations)
   Reinforcement learning (RL) struggles with tasks in which the reward is sparse and binary. The agent almost never observes success, so developers have to hand-craft complex reward functions. The authors from OpenAI propose Hindsight Experience Replay (HER). This technique makes it possible to learn from failed…
2. Neural Random-Access Machines (2015 · 50 citations)
   Kurach, Andrychowicz and Sutskever (Google) ask whether a neural network can learn pointer-based algorithms, which store addresses, follow them and edit memory, using only input-output pairs and backpropagation.

All works

9 works of theirs in our library, the most cited first; 2 with a page here, the others link their original until we summarise them.

1. Overcoming Exploration in Reinforcement Learning with Demonstrations ↗Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · no summary yetAshvin Nair et al.2018 · 708 citations
2. Solving Rubik's Cube with a Robot Hand ↗arXiv:1910.07113 · no summary yetOpenAI et al.2019 · 647 citations
3. Hindsight Experience ReplayarXiv:1707.01495Marcin Andrychowicz, Filip Wolski, Alex Ray, et al.2017 · 421 citations
4. Asymmetric Actor Critic for Image-Based Robot Learning ↗arXiv:1710.06542 · no summary yetLerrel Pinto et al.2018 · 370 citations
5. Parameter Space Noise for Exploration ↗arXiv (Cornell University) · no summary yetMatthias Plappert et al.2017 · 370 citations
6. One-Shot Imitation Learning ↗neural information processing systems · no summary yetYan Duan et al.2017 · 235 citations
7. Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research ↗arXiv (Cornell University) · no summary yetMatthias Plappert et al.2018 · 192 citations
8. Domain Randomization and Generative Models for Robotic Grasping ↗IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · no summary yetJoshua Tobin et al.2018 · 160 citations
9. Neural Random-Access MachinesarXiv:1511.06392Karol Kurach, Marcin Andrychowicz, Ilya Sutskever2015 · 50 citations

🤝 Co-authors here

4 co-authors with a page, the most papers together first.

• Alex Ray
• Ilya Sutskever
• Pieter Abbeel
• Wojciech Zaremba

Venues

Where their works here were published, the most works first, with the editions of those that have a page.

• IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
• Proceedings - IEEE International Conference on Robotics and Automation/Proceedings
• neural information processing systems

🔗 Cited by

Papers of our library cite their works 348 times (of the 149,439 papers whose bibliographies we read); 59 citing papers with a page here →.

Updated 3 November 2026

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/authors/marcin-andrychowicz/