Get started
Author

Steven Kapturowski

Observed name: Kapturowski, Steven
OpenAlex ID: A5060324637
Recurrent Experience Replay in Distributed Reinforcement Learning.
2018 · Steven Kapturowski, Georg Ostrovski, et al. · International Conference on Learning Representations · 308
Agent57: Outperforming the Atari Human Benchmark
2020 · Badia, Adrià Puigdomènech, Piot, Bilal, et al. · arXiv (Cornell University) · 233
PDF
Never Give Up: Learning Directed Exploration Strategies
2020 · Badia, Adrià Puigdomènech, Sprechmann, Pablo, et al. · arXiv (Cornell University) · 196
PDF
Making Efficient Use of Demonstrations to Solve Hard Exploration Problems
2019 · Paine, Tom Le, Gulcehre, Caglar, et al. · arXiv (Cornell University) · 56
PDF
Beyond Fine-Tuning: Transferring Behavior in Reinforcement Learning
2021 · Campos, Víctor, Sprechmann, Pablo, et al. · arXiv (Cornell University) · 13
PDF
Transformers need glasses! Information over-squashing in language tasks
2024 · Federico Barbero, Andrea Banino, et al. · neural information processing systems · 10
PDF
Value-driven Hindsight Modelling
2020 · Guez, Arthur, Viola, Fabio, et al. · arXiv (Cornell University) · 8
PDF
Offline Actor-Critic Reinforcement Learning Scales to Large Models
2024 · Springenberg, Jost Tobias, Abdolmaleki, Abbas, et al. · arXiv (Cornell University) · 7
PDF
Human-level Atari 200x faster
2022 · Kapturowski, Steven, Campos, Víctor, et al. · arXiv (Cornell University) · 7
PDF
Temporal Difference Uncertainties as a Signal for Exploration
2020 · Flennerhag, Sebastian, Wang, Jane X., et al. · arXiv (Cornell University) · 7
PDF
Revisiting Peng's Q($λ$) for Modern Reinforcement Learning
2021 · Kozuno, Tadashi, Tang, Yunhao, et al. · HAL · 4
Coverage as a Principle for Discovering Transferable Behavior in Reinforcement Learning
2021 · Víctor Campos, Pablo Sprechmann, et al. · arXiv (Cornell University) · 3
Revisiting Peng's Q($\lambda$) for Modern Reinforcement Learning
2021 · Tadashi Kozuno, Yunhao Tang, et al. · arXiv (Cornell University) · 1
PDF
Unlocking the Power of Representations in Long-term Novelty-based Exploration
2023 · Saade, Alaa, Kapturowski, Steven, et al. · arXiv (Cornell University)
PDF
Reinforcement learning using density estimation with online clustering for exploration
2023 · Saade, Alaa, Kapturowski, Steven, et al. · HAL
Works count: 15
Citation count: 818
H-index: 7
I10-index: 5
Year
Topic
Type