Georg Ostrovski

Researcher, Google

Researcher, DeepMind

Joined

September 2018

Names

Georg Ostrovski (Preferred)

Emails

****@google.com (Confirmed)

****@gmail.com (Confirmed)

Personal Links

Homepage

DBLP

ORCID

Career & Education History

Researcher

Google (google.com)

2013 – Present

Researcher

DeepMind (deepmind.com)

2013 – Present

PhD student

The University of Warwick (warwick.ac.uk)

2009 – 2013

Advisors, Relations & Conflicts

No relations added

Expertise

No areas of expertise listed

Publications

Deep Reinforcement Learning with Plasticity Injection
Evgenii Nikishin, Junhyuk Oh, Georg Ostrovski, Clare Lyle, Razvan Pascanu, Will Dabney, Andre Barreto
- NeurIPS 2023 spotlight
- Readers: Everyone
Deep Reinforcement Learning with Plasticity Injection
Evgenii Nikishin, Junhyuk Oh, Georg Ostrovski, Clare Lyle, Razvan Pascanu, Will Dabney, Andre Barreto
- Published: 03 Mar 2023, Last Modified: 15 Feb 2026
- RRL 2023 Spotlight
- Readers: Everyone
Quantile Credit Assignment
Thomas Mesnard, Wenqi Chen, Alaa Saade, Yunhao Tang, Mark Rowland, Theophane Weber, Clare Lyle, Audrunas Gruslys, Michal Valko, Will Dabney, Georg Ostrovski, Eric Moulines, Remi Munos
- ICML 2023 OralPoster
- Readers: Everyone
An empirical study of implicit regularization in deep offline RL
Caglar Gulcehre, Srivatsan Srinivasan, Jakub Sygnowski, Georg Ostrovski, Mehrdad Farajtabar, Matthew Hoffman, Razvan Pascanu, Arnaud Doucet
- Accepted by TMLR
- Readers: Everyone
The Phenomenon of Policy Churn
Tom Schaul, Andre Barreto, John Quan, Georg Ostrovski
- Published: 31 Oct 2022, Last Modified: 08 Feb 2026
- NeurIPS 2022 Accept
- Readers: Everyone
When should agents explore?
Miruna Pislar, David Szepesvari, Georg Ostrovski, Diana L Borsa, Tom Schaul
- Published: 28 Jan 2022, Last Modified: 12 Oct 2025
- ICLR 2022 Spotlight
- Readers: Everyone
When should agents explore?
Miruna Pislar, David Szepesvari, Georg Ostrovski, Diana L Borsa, Tom Schaul
- 21 May 2021 (modified: 26 May 2025)
- NeurIPS 2021 Submitted
- Readers: Everyone
The Difficulty of Passive Learning in Deep Reinforcement Learning
Georg Ostrovski, Pablo Samuel Castro, Will Dabney
- Published: 09 Nov 2021, Last Modified: 26 May 2025
- NeurIPS 2021 Poster
- Readers: Everyone
On The Effect of Auxiliary Tasks on Representation Dynamics
Clare Lyle, Mark Rowland, Georg Ostrovski, Will Dabney
- 11 May 2021
- OpenReview Archive Direct Upload
- Readers: Everyone
Temporally-Extended ε-Greedy Exploration
Will Dabney, Georg Ostrovski, Andre Barreto
- Published: 12 Jan 2021, Last Modified: 05 May 2023
- ICLR 2021 Poster
- Readers: Everyone

View all 16 publications

Co-Authors

View all 42 co-authors