Mateusz Ostaszewski

3

Papers

2

Total Citations

Papers (3)

PhysGym: Benchmarking LLMs in Interactive Physics Discovery with Controlled Priors

NeurIPS 2025arXiv

Overestimation, Overfitting, and Plasticity in Actor-Critic: the Bitter Lesson of Reinforcement Learning

Fine-tuning Reinforcement Learning Models is Secretly a Forgetting Mitigation Problem