Michal Bortkiewicz
Contact
News
- Feb 1, 2025: Two papers accepted to ICLR 2025! "Accelerating Goal-Conditioned RL Algorithms and Research" and "Learning Continually by Spectral Regularization" đ
Selected Publications
ICLR 2025: "Accelerating Goal-Conditioned RL Algorithms and Research"
MichaĆ Bortkiewicz, WĆadek PaĆucki, Vivek Myers, Tadeusz Dziarmaga, Tomasz Arczewski, Ćukasz KuciĆski, Benjamin Eysenbach
[Link]
ICLR 2025: "Learning Continually by Spectral Regularization"
Alex Lewandowski, MichaĆ Bortkiewicz, Saurabh Kumar, AndrĂĄs György, Dale Schuurmans, Mateusz Ostaszewski, Marlos C. Machado
[Link]
ICML 2024: "Overestimation, Overfitting, and Plasticity in Action: The Bitter Lesson of Reinforcement Learning"
Michal Nauman*, MichaĆ Bortkiewicz*, Piotr MiĆoĆ, Tomasz TrzciĆski, Mateusz Ostaszewski, Marek Cygan
[Link]
ICML 2024 Spotlight: "Fine-Tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem"
Maciej WoĆczyk, BartĆomiej CupiaĆ, Mateusz Ostaszewski, MichaĆ Bortkiewicz, MichaĆ ZajÄ
c, Razvan Pascanu, Ćukasz KuciĆski, Piotr MiĆoĆ
[Link]
COLA 2023: "The Effectiveness of World Models for Continual Reinforcement Learning"
Samuel Kessler, Mateusz Ostaszewski, MichaĆ Bortkiewicz, Mateusz Ć»arski, Maciej WoĆczyk, Jack Parker-Holder, Stephen J. Roberts, Piotr MiĆoĆ
[Link]
ICRAI 2024: "Subgoal Reachability in Goal-Conditioned Hierarchical Reinforcement Learning"
MichaĆ Bortkiewicz, Jakub Ćyskawa, PaweĆ WawrzyĆski, Mateusz Ostaszewski, Artur Grudkowski, BartĆomiej Sobieski, Tomasz TrzciĆski
[Link]
More available on Google Scholar.
