Maciej Wolczyk

5 papers · 2021–2025 · 4 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 (14)

Venues

ICLR (2) CoRL (1) ICML (1) NeurIPS (1)

Top co-authors

Łukasz Kuciński (3) Razvan Pascanu (3) Bartłomiej Cupiał (2) Piotr Miłoś (2) Michał Zając (2) Johannes von Oswald (1) Rob Fergus (1) Peter Ondruska (1) Lerrel Pinto (1) Błażej Osiński (1)

Research topics

Artificial Intelligence (5) Core AI (4) Machine Learning (3) Reinforcement Learning (3) Methods (3) Learning Types (2) Applications (1) Core Methods (1) Learning Paradigms · Artificial Intelligence (1) Learning Paradigms · Machine Learning (1)

Keywords

reinforcement learning (3) continual learning (1) benchmark evaluation (1) transfer learning (1) decision making (1) continual reinforcement learning (1) compositional generalization (1) continuous control (1) sequential decision (1) forgetting (1) vision-language model (1) soft actor-critic (1) fine tuning (1) knowledge retention (1) urban driving (1) self-driving vehicle (1) large language model (1) differentiable simulator (1) offline policy gradient (1) imitative policy (1)

Papers

BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games ICLR 2025 Discovering modular solutions that generalize compositionally ICLR 2024 Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem ICML 2024 Disentangling Transfer in Continual Reinforcement Learning NeurIPS 2022 Urban Driver: Learning to Drive from Real-world Demonstrations Using Policy Gradients CoRL 2021