Skip to main content

🏢 KTH

Model-free Low-Rank Reinforcement Learning via Leveraged Entry-wise Matrix Estimation
·1610 words·8 mins· loading · loading
Machine Learning Reinforcement Learning 🏢 KTH
LoRa-PI: a model-free RL algorithm learns and exploits low-rank MDP structures for order-optimal sample complexity, achieving ε-optimal policies with O(poly(A)) samples.
If You Want to Be Robust, Be Wary of Initialization
·2056 words·10 mins· loading · loading
AI Theory Robustness 🏢 KTH
Proper weight initialization significantly boosts Graph Neural Network (GNN) and Deep Neural Network (DNN) robustness against adversarial attacks, highlighting a critical, often-overlooked factor.