Michał Bortkiewicz

4 papers · 2024–2025 · 2 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (12)

Venues

ICLR (2) ICML (2)

Top co-authors

Mateusz Ostaszewski (3) Piotr Miłoś (2) Łukasz Kuciński (2) Bartłomiej Cupiał (1) Władysław Pałucki (1) Alex Lewandowski (1) Tomasz Trzcinski (1) Maciej Wolczyk (1) Vivek Myers (1) Tadeusz Dziarmaga (1)

Research topics

Machine Learning (3) Learning Types (3) Artificial Intelligence (2) Reinforcement Learning (2) Core AI (2) Methods (2) Deep Learning (1) Applications (1) Learning Paradigms (1) Optimization & Theory (1) Techniques (1)

Keywords

contrastive learning (1) reinforcement learning (1) continual learning (1) regularization (1) self-supervised learning (1) spectral regularization (1) forgetting (1) plasticity loss (1) goal-conditioned reinforcement learning (1) loss of plasticity (1) soft actor-critic (1) singular value (1) agent system (1) fine tuning (1) knowledge retention (1) gradient diversity (1) overfitting (1) overestimation (1) gradient update steps (1) pre-trained capabilities (1)

Papers

Accelerating Goal-Conditioned Reinforcement Learning Algorithms and Research ICLR 2025 Learning Continually by Spectral Regularization ICLR 2025 Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem ICML 2024 Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning ICML 2024